© 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. 19-TRANSCODER-HP
    7. 9085
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    akov
    -0.30
    within
    -0.25
    sat
    -0.25
    zie
    -0.25
    èĥ½æĬĬ
    -0.25
     diam
    -0.24
    agues
    -0.24
    Ø´Ùħ
    -0.24
    _DIRECTORY
    -0.24
    presso
    -0.24
    POSITIVE LOGITS
    TEX
    0.30
    éĢļ
    0.28
     laps
    0.27
     len
    0.26
     liberal
    0.26
    åı¦ä¸Ģæĸ¹éĿ¢
    0.25
     porous
    0.25
    辫
    0.25
    -long
    0.25
    æľ¬èĥ½
    0.25
    Activations Density 0.052%

    No Known Activations

    This feature has no known activations.