© 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. 19297
    Prev
    Next
    INDEX
    Explanations

    Code/web content

    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
    zon
    -0.27
    ç¯
    -0.27
    éĥ¨
    -0.26
    å¨ĥ
    -0.24
    ajar
    -0.24
     Sons
    -0.23
    ajes
    -0.23
     Tweet
    -0.23
     getList
    -0.23
     drill
    -0.23
    POSITIVE LOGITS
    gel
    0.27
    оÑĤ
    0.25
    _NEG
    0.23
    ugs
    0.23
    åįİ
    0.23
    _flip
    0.23
    åį£
    0.23
     Midnight
    0.23
    åħ¨
    0.23
    git
    0.23
    Activations Density 0.039%

    No Known Activations