© 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. 18638
    Prev
    Next
    INDEX
    Explanations

    technical summaries

    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
    icol
    -0.30
    æĶ¹åĸĦ
    -0.26
     Scan
    -0.25
    rael
    -0.25
     root
    -0.25
    eel
    -0.25
    BOOL
    -0.24
    colon
    -0.24
    éĽĨä¸Ń
    -0.24
     ServiceException
    -0.24
    POSITIVE LOGITS
    iphy
    0.29
    顺
    0.26
     Spir
    0.25
    spir
    0.25
    é¦
    0.25
    stand
    0.24
     Circular
    0.24
     Monaco
    0.24
    otify
    0.24
    pest
    0.24
    Activations Density 1.760%

    No Known Activations