© 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. 17903
    Prev
    Next
    INDEX
    Explanations

    Manufacturing and production methods

    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
    ritt
    -0.27
    对åѦçĶŁ
    -0.26
    bins
    -0.26
     Scot
    -0.25
     Rath
    -0.25
     cursed
    -0.24
     Ã¶ÄŁrenc
    -0.24
    utura
    -0.24
    polit
    -0.24
    å®īåİ¿
    -0.24
    POSITIVE LOGITS
    åĮĻ
    0.26
    çľŁç©º
    0.25
    Sig
    0.24
    Truthy
    0.24
    顶
    0.24
    ä¼ł
    0.23
    chip
    0.23
     mama
    0.23
    resse
    0.23
    å±ĬæŶ
    0.23
    Activations Density 0.104%

    No Known Activations