© 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. 19974
    Prev
    Next
    INDEX
    Explanations

    once away

    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
    å¿«
    -0.39
     instant
    -0.39
     Instant
    -0.36
    instant
    -0.35
    Instant
    -0.33
    å¿«éĢŁ
    -0.33
     fast
    -0.33
     rapid
    -0.31
    ç«ĭ马
    -0.31
     quick
    -0.30
    POSITIVE LOGITS
     once
    0.80
    once
    0.74
     Once
    0.61
    Once
    0.61
     away
    0.60
    away
    0.47
    ä¸Ģ次
    0.46
    -away
    0.45
     Away
    0.45
    .once
    0.45
    Activations Density 0.072%

    No Known Activations