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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 36395
    Prev
    Next
    INDEX
    Explanations

    negative situations/complaints

    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
     "[
    -0.06
    [df
    -0.06
     -->
    -0.06
     mechanisms
    -0.06
    קיר
    -0.06
     $('#
    -0.06
     tb
    -0.06
     소
    -0.06
    “You
    -0.06
     vo
    -0.06
    POSITIVE LOGITS
    FormatException
    0.08
    Plug
    0.07
    ustainability
    0.07
    uggy
    0.07
    运动会
    0.07
    .liferay
    0.07
    胙
    0.07
    褴
    0.07
     Elementary
    0.07
    structuring
    0.07
    Activations Density 0.106%

    No Known Activations