© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 17755
    Prev
    Next
    INDEX
    Explanations

    lion

    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
    Negative Logits
    人们对
    -0.27
     roma
    -0.26
    éķľå¤´
    -0.26
     LTC
    -0.26
    æľĽ
    -0.26
    calc
    -0.25
    cts
    -0.25
     Catal
    -0.25
     Swe
    -0.24
    _xs
    -0.24
    POSITIVE LOGITS
    ensen
    0.32
     male
    0.30
    ени
    0.29
    ense
    0.29
    ene
    0.29
    enti
    0.28
    çĶ·
    0.27
    ning
    0.27
    ess
    0.26
    eni
    0.26
    Activations Density 0.157%

    No Known Activations