Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 87140
    Prev
    Next
    INDEX
    Explanations

    negative events

    np_max-act · gemini-2.0-flash

    Words that express strong negative impact, danger, or sensational severity (e.g., disaster/havoc/doom-type terms).

    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
     Supplies
    -0.08
     wygląda
    -0.07
    �
    -0.07
     invite
    -0.07
     Diesel
    -0.07
     listBox
    -0.07
     apprec
    -0.07
    -transitional
    -0.07
    拜师学艺
    -0.07
    institution
    -0.07
    POSITIVE LOGITS
    과
    0.07
    평
    0.07
    عن
    0.07
    追究
    0.07
    进展
    0.06
     declined
    0.06
    enza
    0.06
    那
    0.06
    iap
    0.06
    çek
    0.06
    Activations Density 1.363%

    No Known Activations