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. 48410
    Prev
    Next
    INDEX
    Explanations

    Erotic texts

    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
    𝐬
    -0.07
    (STD
    -0.07
    >J
    -0.07
    .Unit
    -0.07
    긱
    -0.07
     mitt
    -0.06
    (TRUE
    -0.06
    _mouse
    -0.06
    溯源
    -0.06
     deserted
    -0.06
    POSITIVE LOGITS
     Possible
    0.08
     선택
    0.07
    ethod
    0.07
    AAF
    0.07
    /widget
    0.07
     некоторых
    0.07
    として
    0.07
    sword
    0.07
     Ability
    0.06
    全力以
    0.06
    Activations Density 0.026%

    No Known Activations