© 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. 19469
    Prev
    Next
    INDEX
    Explanations

    video graphics

    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
    æīĵæĸŃ
    -0.27
    æ¡ħ
    -0.26
    alpha
    -0.25
     Alpha
    -0.24
     alpha
    -0.24
    .oracle
    -0.24
    Alpha
    -0.24
    æĴ¸
    -0.24
     reporters
    -0.23
    Canonical
    -0.23
    POSITIVE LOGITS
     video
    0.32
     graph
    0.31
    Vac
    0.29
     vide
    0.29
    video
    0.29
    nic
    0.29
     íĺ¸
    0.28
    åĽ¾å½¢
    0.28
     detailing
    0.28
     graphic
    0.27
    Activations Density 1.321%

    No Known Activations