© 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. 18779
    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
     LD
    -0.28
     safety
    -0.25
     inf
    -0.25
     AUTHORS
    -0.25
     f
    -0.24
     business
    -0.24
    adar
    -0.24
    f
    -0.24
     conditioning
    -0.24
     tread
    -0.24
    POSITIVE LOGITS
    atham
    0.29
    éĻIJéĩı
    0.28
    åħĭ
    0.28
    涨
    0.28
    IMO
    0.26
    stitial
    0.26
    æ¹Ħ
    0.26
    ANI
    0.26
    IDEO
    0.25
    å±Ĭ
    0.25
    Activations Density 0.786%

    No Known Activations

    This feature has no known activations.