© 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. 112584
    Prev
    Next
    INDEX
    Explanations

    English text fragments

    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
     {
    -0.28
     while
    -0.27
    —
    -0.27
    igital
    -0.27
    °
    -0.26
    OCK
    -0.26
    ep
    -0.26
    ä¸Ŀ
    -0.25
     °
    -0.25
     ('
    -0.25
    POSITIVE LOGITS
    .inspect
    0.27
    .populate
    0.27
    otate
    0.26
     decltype
    0.25
    DataReader
    0.25
     aÅŁ
    0.25
    GameState
    0.25
     allowances
    0.24
    sgiving
    0.24
     foreclosure
    0.23
    Activations Density 0.004%

    No Known Activations