© 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. 31-TRANSCODER-HP
    7. 19235
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÐIJлекÑģан
    -0.38
     ÐĶмиÑĤÑĢ
    -0.33
     Porno
    -0.33
     ÐŁÐ¾Ñĩем
    -0.33
     Câm
    -0.32
     councillors
    -0.31
    ÑĩÑĢежден
    -0.31
    Ø£ÙĪضاع
    -0.31
    индивид
    -0.31
     councillor
    -0.31
    POSITIVE LOGITS
    1
    0.43
     (
    0.42
    0.42
     Feedback
    0.40
     In
    0.40
     M
    0.40
     The
    0.39
     Ice
    0.39
    -
    0.39
     $
    0.39
    Activations Density 10.120%

    No Known Activations

    This feature has no known activations.