© 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. 9253
    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
    ush
    -0.27
    emento
    -0.27
     Swe
    -0.25
    æĻ¤
    -0.25
     één
    -0.24
    æīĭä¸Ĭ
    -0.24
    ti
    -0.24
    ee
    -0.24
    æĶ¾åĩº
    -0.23
    ahun
    -0.23
    POSITIVE LOGITS
     tÃł
    0.30
    ä½ĵè´¨
    0.29
    ape
    0.28
    æİIJ
    0.28
    åįķåħĥ
    0.26
    åĽ½æ°ijç»ıæµİ
    0.26
    .ny
    0.25
    ities
    0.25
    developers
    0.25
    çļĦåĬĽéĩı
    0.24
    Activations Density 0.080%

    No Known Activations

    This feature has no known activations.