© 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. 97124
    Prev
    Next
    INDEX
    Explanations

    recovery, identification, discovery

    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
     treating
    -0.26
     orthogonal
    -0.25
     Wort
    -0.24
    éŨæĪ·ç½ijç«Ļ
    -0.24
     Fork
    -0.24
    çŃ¾çº¦ä»ªå¼ı
    -0.24
    èªł
    -0.24
    oric
    -0.24
    pret
    -0.24
    appa
    -0.23
    POSITIVE LOGITS
     recovery
    0.44
     Recovery
    0.38
     recover
    0.38
     identified
    0.38
     recovered
    0.36
     bulund
    0.35
    æģ¢å¤į
    0.35
     found
    0.35
    å¤įèĭı
    0.34
     locate
    0.34
    Activations Density 0.104%

    No Known Activations