© 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. 88303
    Prev
    Next
    INDEX
    Explanations

    Code, filenames, names

    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
    æļĹæļĹ
    -0.24
    ÅĽci
    -0.24
    zin
    -0.24
    FLOAT
    -0.23
    .si
    -0.23
     FACT
    -0.23
     Follow
    -0.23
     Forward
    -0.23
    csr
    -0.23
     Bonus
    -0.22
    POSITIVE LOGITS
    æŶåĢĻ
    0.29
    thead
    0.28
    .hasOwnProperty
    0.26
    ised
    0.26
    ows
    0.26
    åŀł
    0.26
    头
    0.25
    头çĹĽ
    0.24
    Ľå»º
    0.24
    çŀŃ解
    0.24
    Activations Density 0.023%

    No Known Activations