© 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. 54480
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous web documents

    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
    Not in Any Lists

    No Comments

    Negative Logits
    éĵ¶
    -0.28
    etimes
    -0.28
    åŁ¹åħ»åѦçĶŁ
    -0.28
    Sk
    -0.27
    erule
    -0.27
    Hint
    -0.27
    lec
    -0.27
     Sk
    -0.27
    ichi
    -0.27
    çķ¥
    -0.26
    POSITIVE LOGITS
    .ctrl
    0.26
    -dist
    0.25
    _da
    0.25
    dist
    0.25
    ç»ĺ
    0.25
    verb
    0.25
     neighb
    0.24
    boards
    0.24
    REN
    0.24
    æĴ¥
    0.24
    Activations Density 0.012%

    No Known Activations