© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7344
    Prev
    Next
    INDEX
    Explanations

    Code/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utz
    -0.32
    _EXTENSIONS
    -0.31
    rai
    -0.27
    riad
    -0.27
    DCF
    -0.27
    hausen
    -0.27
    REEN
    -0.25
     SUS
    -0.25
    rita
    -0.24
    uez
    -0.24
    POSITIVE LOGITS
    ÂŃs
    0.30
     hw
    0.28
    etri
    0.27
    /autoload
    0.27
     Prem
    0.25
    éħ¸
    0.24
    æľ¬æĬ¥è®°èĢħ
    0.24
    夺
    0.23
    archs
    0.23
    äºĮç»´çłģ
    0.23
    Activations Density 0.010%

    No Known Activations