© 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. 130557
    Prev
    Next
    INDEX
    Explanations

    so

    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
    IW
    -0.26
    _IW
    -0.25
    çĻ»åľº
    -0.25
    侬
    -0.24
    $$$
    -0.24
    ä¸į对
    -0.24
    æĥĬ人
    -0.24
    GRE
    -0.24
    e
    -0.24
     pls
    -0.23
    POSITIVE LOGITS
    ä¸ĸçķĮçļĦ
    0.28
    éĤ¦
    0.27
     other
    0.26
     tun
    0.25
     ident
    0.24
    aras
    0.24
    .scala
    0.24
     mens
    0.24
     worlds
    0.24
     tb
    0.23
    Activations Density 0.023%

    No Known Activations