© 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. 98508
    Prev
    Next
    INDEX
    Explanations

    Someone stating something

    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
     <",
    -0.29
    @",
    -0.29
    å²ģçļĦ
    -0.28
     =",
    -0.28
     ",č↵
    -0.27
    =',
    -0.27
    _č↵č↵
    -0.27
     ,č↵
    -0.27
    {}]
    -0.26
     ],č↵
    -0.26
    POSITIVE LOGITS
    CS
    0.28
    Full
    0.27
     own
    0.27
    ;
    0.27
     Own
    0.26
     ign
    0.26
    CD
    0.25
    Ast
    0.25
    ---
    0.25
    /cs
    0.25
    Activations Density 0.004%

    No Known Activations