© 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. 97775
    Prev
    Next
    INDEX
    Explanations

    Varied casual text sources

    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
     Pod
    -0.25
    indre
    -0.25
     IDX
    -0.25
    ounter
    -0.24
     Bing
    -0.24
    è¯ĺ
    -0.24
     underst
    -0.24
    UBE
    -0.24
    seat
    -0.23
    iom
    -0.23
    POSITIVE LOGITS
    æ·
    0.26
     friend
    0.25
    жÑĥ
    0.25
    æľĭåıĭ
    0.25
    æĴ
    0.25
     chops
    0.24
    èħŃ
    0.23
    hy
    0.23
    åĪłéĻ¤æĪIJåĬŁ
    0.23
     бо
    0.23
    Activations Density 0.003%

    No Known Activations