© 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. 7872
    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
    <?↵
    -0.27
    éĢı
    -0.26
    _PE
    -0.25
    ter
    -0.25
     vern
    -0.24
    å¤įåį°
    -0.24
     Forrest
    -0.24
     sign
    -0.24
    antom
    -0.23
     pe
    -0.23
    POSITIVE LOGITS
    UIT
    0.32
    ocode
    0.28
     differentiated
    0.27
    ä½ıäºĨ
    0.26
    ç½Ĺ马
    0.26
    ferences
    0.25
    _rom
    0.25
     diffé
    0.25
    fer
    0.25
    Rom
    0.24
    Activations Density 0.301%

    No Known Activations

    This feature has no known activations.