© 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. 8051
    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
    fills
    -0.26
    AIN
    -0.25
    æµ·æ´ĭ
    -0.24
    éĩı
    -0.24
     nouns
    -0.24
     Mit
    -0.24
    SSERT
    -0.23
     Nos
    -0.23
     intimacy
    -0.23
    mit
    -0.23
    POSITIVE LOGITS
    _don
    0.29
    quake
    0.27
    bidden
    0.26
    don
    0.26
    å¼ĥ
    0.25
    견
    0.25
    coli
    0.24
    /remove
    0.24
    çĶ³åįļ
    0.24
    åįĬ天
    0.24
    Activations Density 1.203%

    No Known Activations

    This feature has no known activations.