© 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. 18183
    Prev
    Next
    INDEX
    Explanations

    scientific/technical texts

    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
    iasi
    -0.33
    IAS
    -0.28
    Species
    -0.27
    尺度
    -0.26
    _species
    -0.26
    人人éĥ½
    -0.26
    æ³½è¿ŀ
    -0.25
    storm
    -0.25
    elier
    -0.25
    åѦä½į
    -0.25
    POSITIVE LOGITS
     bang
    0.28
    /font
    0.28
    女
    0.27
    å©´
    0.26
    ard
    0.25
    aret
    0.25
    æĮ¥
    0.25
    çħĮ
    0.25
    arms
    0.24
    bens
    0.24
    Activations Density 0.004%

    No Known Activations