© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 41103
    Prev
    Next
    INDEX
    Explanations

    patents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .nz
    -0.32
    è¯
    -0.29
    è¿Ļæł·ä¸Ģ
    -0.28
    losure
    -0.28
    åĽ´
    -0.25
    CLAIM
    -0.25
     exactly
    -0.25
    èĭ«
    -0.25
     доÑģÑĤ
    -0.25
    ensed
    -0.24
    POSITIVE LOGITS
    thal
    0.32
    æ¯į亲
    0.25
     @$
    0.24
    ulis
    0.24
    Mother
    0.23
     Blocks
    0.23
    åĩºèī²çļĦ
    0.23
    æĸ¯åĿ¦
    0.23
    åľ©
    0.23
     rá
    0.23
    Activations Density 0.009%

    No Known Activations