© 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. 20-TRANSCODER-HP
    7. 129822
    Prev
    Next
    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shading
    -0.28
     finding
    -0.27
    ocz
    -0.27
    为æ°ij
    -0.26
    æ¯ķç«Ł
    -0.26
    finding
    -0.26
    boxed
    -0.26
     stepping
    -0.25
    æ¾į
    -0.24
    ãģ¾ãģĹãģ¦
    -0.24
    POSITIVE LOGITS
    rodu
    0.28
     collide
    0.26
     Tig
    0.25
    IDI
    0.25
    pollo
    0.25
     Rig
    0.25
     Polic
    0.24
    lassen
    0.24
    anus
    0.24
    è¿Ļä¸ī个
    0.24
    Activations Density 15.480%

    No Known Activations