© 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. 23-TRANSCODER-HP
    7. 25565
    Prev
    Next
    INDEX
    Explanations

    nor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ°¸è¿ľ
    -0.26
    ä¸įèĥ½åĨį
    -0.25
    RequiredMixin
    -0.25
    Playable
    -0.24
    ä¸įåģľ
    -0.24
    åĩºåĽ½
    -0.24
    ubi
    -0.24
     shouldn
    -0.24
    ius
    -0.23
    ķĮ
    -0.23
    POSITIVE LOGITS
     anything
    0.41
    ä»»ä½ķä¸Ģ个
    0.33
    èĢĮæĺ¯
    0.32
    anything
    0.32
    ä»»ä½ķ人
    0.32
     anymore
    0.32
     nor
    0.31
     otherwise
    0.31
     Anything
    0.30
     anyone
    0.28
    Activations Density 0.034%

    No Known Activations