© 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. 52897
    Prev
    Next
    INDEX
    Explanations

    comp

    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
    çİĩ为
    -0.31
    este
    -0.28
    eties
    -0.26
    éĿ¡
    -0.26
     RuntimeError
    -0.25
     co
    -0.25
    ges
    -0.25
    gage
    -0.24
    lo
    -0.24
    åįı
    -0.23
    POSITIVE LOGITS
    <Action
    0.35
    visitor
    0.28
    åįĥåħĥ
    0.28
    action
    0.28
     trait
    0.27
    éĢĢè¿ĺ
    0.26
    trait
    0.26
    å¼ĢæĶ¯
    0.25
    ä¹ŁçŁ¥éģĵ
    0.25
    lyph
    0.25
    Activations Density 0.022%

    No Known Activations