© 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. 130572
    Prev
    Next
    INDEX
    Explanations

    Places

    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
    å±ĢéĻIJ
    -0.28
    lik
    -0.25
     hum
    -0.25
    lessly
    -0.25
    æľĢç»Ī
    -0.25
    Hum
    -0.24
     Thousand
    -0.24
    /stretch
    -0.24
    aho
    -0.24
    ä¸ŃåĽ½åĽ½éĻħ
    -0.24
    POSITIVE LOGITS
    realm
    0.29
    caret
    0.27
    建设çĶ¨åľ°
    0.26
    å¾Īæ¸ħæ¥ļ
    0.26
    áng
    0.26
    wagon
    0.26
    ä¸Ģå°ģ
    0.25
    renal
    0.25
     lég
    0.24
    ·æĸ°
    0.24
    Activations Density 0.030%

    No Known Activations