© 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. 97945
    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
    ä¾ĽåĽ¾
    -0.29
    æĹ¥è®¯
    -0.26
    æıIJ
    -0.26
    è°Ĵ
    -0.26
    壳
    -0.26
    ecc
    -0.26
    é¢Ĩ
    -0.26
    bsd
    -0.25
    NON
    -0.25
    erves
    -0.25
    POSITIVE LOGITS
     Pearson
    0.27
    ential
    0.27
    nder
    0.26
     ↵    ↵
    0.25
     middle
    0.25
     hoe
    0.25
    alse
    0.24
     ;
    0.24
     evolution
    0.24
     marketplace
    0.24
    Activations Density 0.087%

    No Known Activations