© 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. 6941
    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
    ppv
    -0.27
    çĽĬ
    -0.25
    .esp
    -0.24
    ¾ç¤º
    -0.24
    ',['../
    -0.24
    ::~
    -0.24
     pave
    -0.23
    ãĥĭãĥ¥ãĥ¼ãĤ¹
    -0.23
    æĽ´æĺ¯
    -0.23
    .ws
    -0.22
    POSITIVE LOGITS
    è°Ĵ
    0.29
    ÑģмоÑĤÑĢ
    0.28
     reun
    0.28
    æĦıåij³
    0.27
    ä»ŀ
    0.26
    iteral
    0.25
    uala
    0.25
     Trey
    0.24
     bomb
    0.24
    otel
    0.24
    Activations Density 0.292%

    No Known Activations

    This feature has no known activations.