© 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. 9-TRANSCODER-HP
    7. 29520
    Prev
    Next
    INDEX
    Explanations

    Spanish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ËĬ
    -0.31
     Sour
    -0.30
    ди
    -0.28
    鼳
    -0.27
    ahn
    -0.27
    è·¯åĨµ
    -0.26
    rell
    -0.25
    ERAL
    -0.25
    quir
    -0.25
    ique
    -0.24
    POSITIVE LOGITS
    主é¢ĺæ´»åĬ¨
    0.29
     vids
    0.27
    iefs
    0.27
    æ´»åĬ¨ä¸Ń
    0.25
    è¡Įäºĭ
    0.25
     brows
    0.25
    纸ä¸Ĭ
    0.25
     cookbook
    0.24
    æѤæ¡Ī
    0.24
    éĺ»åĬĽ
    0.24
    Activations Density 0.285%

    No Known Activations