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. 19-RESID-POST-AA
    6. 7271
    Prev
    Next
    INDEX
    Explanations

    Numerical data and statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mixture
    -0.07
     ($('#
    -0.07
     featuring
    -0.07
    חוסר
    -0.07
    缬
    -0.07
    电视台
    -0.07
     Cottage
    -0.06
    삠
    -0.06
     tome
    -0.06
    OptionsMenu
    -0.06
    POSITIVE LOGITS
     Emails
    0.07
    ~↵↵
    0.07
     %↵
    0.07
     Implement
    0.07
     #↵↵
    0.07
    %↵
    0.07
     []);↵
    0.07
    READY
    0.06
    faker
    0.06
    />.↵↵
    0.06
    Activations Density 0.023%

    No Known Activations