© 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. 18580
    Prev
    Next
    INDEX
    Explanations

    wound

    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
    ième
    -0.26
    hoc
    -0.26
    sar
    -0.25
    éħIJ
    -0.25
    skill
    -0.25
     NDEBUG
    -0.25
    CHED
    -0.24
     CoreData
    -0.24
    metrical
    -0.24
    ãģ£ãģıãĤĬ
    -0.24
    POSITIVE LOGITS
     left
    0.53
    left
    0.43
    Left
    0.41
    _left
    0.38
     Left
    0.37
    -left
    0.35
     LEFT
    0.35
    å·¦
    0.34
    .left
    0.33
    /left
    0.33
    Activations Density 0.027%

    No Known Activations