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. 36441
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    𦝼
    -0.08
    untas
    -0.07
     tutorials
    -0.07
    typeid
    -0.07
    ToggleButton
    -0.07
    👤
    -0.07
     tup
    -0.07
    ชะ
    -0.07
     gifs
    -0.06
     المعلومات
    -0.06
    POSITIVE LOGITS
     Gener
    0.07
    @Json
    0.07
    -ab
    0.07
    HIGH
    0.06
    력을
    0.06
    },${
    0.06
    _FIRE
    0.06
    mention
    0.06
     walkers
    0.06
    的成本
    0.06
    Activations Density 0.128%

    No Known Activations