© 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. 64260
    Prev
    Next
    INDEX
    Explanations

    Fluids and consumable items

    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
    acr
    -0.27
     tack
    -0.27
    Appro
    -0.26
    Accept
    -0.25
    TargetException
    -0.25
    à¸Ħล
    -0.24
    Yeah
    -0.24
    (objects
    -0.24
    cac
    -0.23
    leaf
    -0.23
    POSITIVE LOGITS
    ?,?,?,?,
    0.28
    SWG
    0.28
     congressional
    0.28
    第ä¸ĢæĿ¡
    0.28
    æīĢåľ¨
    0.27
     moderators
    0.26
    ?,?,
    0.26
    èĤ¡ä¸ľå¤§ä¼ļ
    0.26
    æīĢåľ¨çļĦ
    0.25
     proposition
    0.25
    Activations Density 8.102%

    No Known Activations