© 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. 18-TRANSCODER-HP
    7. 88579
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azen
    -0.27
    andid
    -0.26
    enido
    -0.25
    榷
    -0.25
     Federation
    -0.24
     двоÑĢ
    -0.24
    æĪĸåħ¶ä»ĸ
    -0.24
    ç½²
    -0.24
    å¾Ī好
    -0.24
    .dc
    -0.24
    POSITIVE LOGITS
    resher
    0.32
     Reputation
    0.28
    æĸ°é²ľ
    0.28
    айн
    0.27
     heavier
    0.27
    æĽ´èĥ½
    0.27
    shortcut
    0.25
    çľ¼æ³ª
    0.25
     Resolution
    0.25
     memorable
    0.25
    Activations Density 4.703%

    No Known Activations