© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 23380
    Prev
    Next
    INDEX
    Explanations

    circumstances beyond control

    np_max-act · gemini-2.0-flash

    mentions of contractual force majeure or other events described as beyond a party's reasonable control or unforeseeable circumstances.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kod
    -0.08
    also
    -0.07
    碲
    -0.07
    略
    -0.07
    舴
    -0.06
    -SA
    -0.06
    讹
    -0.06
     الواحد
    -0.06
    趁
    -0.06
     kod
    -0.06
    POSITIVE LOGITS
    队长
    0.08
    .W
    0.07
    recursive
    0.07
    Петербур
    0.07
    :name
    0.07
     recursive
    0.07
    Regression
    0.07
    风控
    0.06
    Pressure
    0.06
    渗
    0.06
    Activations Density 0.036%

    No Known Activations