© 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. 97138
    Prev
    Next
    INDEX
    Explanations

    resistance

    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
    .appspot
    -0.30
     Sche
    -0.30
    èµ°
    -0.26
    ç³Ł
    -0.26
    å®ļéĩı
    -0.25
     Lad
    -0.25
    大äºĭ
    -0.25
    loud
    -0.25
    лоÑĤ
    -0.24
    /manual
    -0.24
    POSITIVE LOGITS
     resistance
    0.57
     resist
    0.55
     resistant
    0.54
     drug
    0.54
    èĢIJ
    0.49
     Resistance
    0.45
    -resistant
    0.45
     Resist
    0.45
     resisted
    0.44
    Resistance
    0.44
    Activations Density 0.888%

    No Known Activations