© 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. 33-TRANSCODER-HP
    7. 54716
    Prev
    Next
    INDEX
    Explanations

    break

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çĩķ
    -0.26
     NX
    -0.26
    bet
    -0.26
     Hamp
    -0.25
     bet
    -0.25
     Ang
    -0.24
    ypress
    -0.24
    TX
    -0.24
    ango
    -0.24
    æĸĩåѦ
    -0.24
    POSITIVE LOGITS
     break
    0.40
     breaks
    0.37
    .break
    0.34
    _break
    0.32
    /github
    0.31
     BREAK
    0.31
    pus
    0.30
    éĻ¬
    0.29
     breakout
    0.29
    Break
    0.28
    Activations Density 0.026%

    No Known Activations