© 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. 112241
    Prev
    Next
    INDEX
    Explanations

    Code and miscellaneous text

    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
    acı
    -0.26
    uja
    -0.25
    enko
    -0.24
    lıkl
    -0.24
    ç²¾åĬĽ
    -0.24
    ="[
    -0.24
     decrement
    -0.23
    yyyy
    -0.23
    wij
    -0.23
    /el
    -0.23
    POSITIVE LOGITS
    овоÑĢ
    0.25
    .layouts
    0.24
    a
    0.23
    _basis
    0.23
    nish
    0.23
    eted
    0.23
    çĢļ
    0.23
    olution
    0.22
    åħ¥å¸Ĥ
    0.22
     inv
    0.22
    Activations Density 0.004%

    No Known Activations