© 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. 98137
    Prev
    Next
    INDEX
    Explanations

    ^

    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
    çĻ½è¡£
    -0.25
    $txt
    -0.24
    ç³ľ
    -0.23
    ĵåIJį
    -0.23
    е
    -0.23
    ç²®
    -0.23
    lector
    -0.23
    æĸ°èĤ¡
    -0.23
    ä¸Ģæī¹
    -0.23
    让æ¶Īè´¹èĢħ
    -0.23
    POSITIVE LOGITS
     htonl
    0.27
    åĭ¿
    0.25
    èĮĥçķ´
    0.25
    åĮĢ
    0.25
    çĶ¨éĩı
    0.25
    èĦī
    0.25
    alic
    0.24
    .serv
    0.24
     deduct
    0.24
    rowse
    0.24
    Activations Density 0.021%

    No Known Activations