© 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. 19470
    Prev
    Next
    INDEX
    Explanations

    News articles

    np_max-act-logits · gemini-2.0-flash
    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
     lique
    -0.28
    ç®Ĺ
    -0.28
     ten
    -0.26
     lit
    -0.26
    oric
    -0.26
    伦æķ¦
    -0.25
    lit
    -0.25
    ÑĢоÑĪ
    -0.25
    Ñĥгл
    -0.25
    åįģ
    -0.24
    POSITIVE LOGITS
    ozy
    0.27
    morph
    0.26
     segregation
    0.26
    wyn
    0.26
    åģĥ
    0.25
     Swim
    0.24
    ittings
    0.24
    åķĨ
    0.24
    æİĸ
    0.24
    æ³³
    0.24
    Activations Density 27.038%

    No Known Activations