© 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. 141003
    Prev
    Next
    INDEX
    Explanations

    look

    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
     anonymously
    -0.27
     åĪłéĻ¤
    -0.26
    uw
    -0.26
    ä¸įéĶĪ
    -0.25
    CID
    -0.25
    ToDelete
    -0.25
     usern
    -0.25
    æĬķ稿
    -0.25
     CONTRIBUTORS
    -0.25
     IH
    -0.25
    POSITIVE LOGITS
    èĪį
    0.30
    ç»´
    0.28
    åħĥ
    0.28
    纪
    0.27
    ute
    0.27
    æĢĢ
    0.27
     profile
    0.27
     ut
    0.26
     (
    0.26
    verb
    0.25
    Activations Density 12.697%

    No Known Activations