© 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. 87541
    Prev
    Next
    INDEX
    Explanations

    vul

    np_max-act · gemini-2.0-flash
    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
    serde
    -0.07
    attery
    -0.07
    -dom
    -0.07
    mé
    -0.07
    能得到
    -0.07
     belang
    -0.07
    brace
    -0.07
    ;if
    -0.07
    benef
    -0.07
     earthquakes
    -0.07
    POSITIVE LOGITS
    出口
    0.08
    中小企业
    0.07
    phalt
    0.07
    بو
    0.07
    	th
    0.07
    ollapse
    0.07
    Buy
    0.07
    Holy
    0.06
     Testing
    0.06
    嵝
    0.06
    Activations Density 0.004%

    No Known Activations