© 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. 95065
    Prev
    Next
    INDEX
    Explanations

    Short interjections

    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
     scars
    -0.28
    éĴ¢
    -0.27
    ietf
    -0.26
    etal
    -0.26
    yü
    -0.25
    /result
    -0.24
    éĭ¼
    -0.24
    èµĶ
    -0.24
    reeze
    -0.24
    巨人
    -0.23
    POSITIVE LOGITS
     ep
    0.60
     ah
    0.56
    ah
    0.52
    aha
    0.50
     Ah
    0.50
     Ep
    0.50
    ahas
    0.45
    Ah
    0.45
    Ep
    0.43
    AH
    0.43
    Activations Density 0.883%

    No Known Activations