© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 111529
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stav
    -0.29
    lectron
    -0.27
    _dash
    -0.24
    ResponseType
    -0.24
    Associate
    -0.24
     ticking
    -0.24
    éĺ²åį«
    -0.23
    åıij
    -0.23
    agnitude
    -0.23
    acas
    -0.23
    POSITIVE LOGITS
     August
    0.26
    oho
    0.25
    HttpStatus
    0.25
    uggy
    0.24
    æijĺè¦ģ
    0.24
     company
    0.24
    /cs
    0.24
    inheritdoc
    0.23
    ##↵↵
    0.23
    >[]
    0.23
    Activations Density 0.001%

    No Known Activations