© 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. 97499
    Prev
    Next
    INDEX
    Explanations

    Technical documents

    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
    cri
    -0.25
    è°Ł
    -0.24
    åĽº
    -0.24
    _CM
    -0.24
     quý
    -0.24
    emp
    -0.23
    resp
    -0.23
    smith
    -0.23
    tle
    -0.23
     Quý
    -0.23
    POSITIVE LOGITS
    yh
    0.27
    setContent
    0.27
    overs
    0.26
    æĸ°éĹ»ç½ij
    0.25
    té
    0.25
    éĩįè¦ģåĨħ容
    0.24
    /tab
    0.23
    ĥģ
    0.23
     conferences
    0.23
    _again
    0.23
    Activations Density 0.004%

    No Known Activations