© 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. 30-TRANSCODER-HP
    7. 96997
    Prev
    Next
    INDEX
    Explanations

    Code and special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Hurt
    -0.28
    HV
    -0.27
    annon
    -0.26
     manifest
    -0.25
    annie
    -0.25
    Lv
    -0.25
    ammen
    -0.24
    åĬ¨ä½ľ
    -0.24
     multip
    -0.24
     adversity
    -0.24
    POSITIVE LOGITS
     sweep
    0.25
    wh
    0.25
    çŃ¾è®¢
    0.25
    çªĿ
    0.24
     scalable
    0.24
    esters
    0.24
    strup
    0.24
    çĽijå¯Ł
    0.24
    _store
    0.24
    atical
    0.24
    Activations Density 0.100%

    No Known Activations