© 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. 94889
    Prev
    Next
    INDEX
    Explanations

    curve

    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
    YLE
    -0.28
    eken
    -0.27
    auer
    -0.27
    çĶŁæ´»
    -0.26
     living
    -0.26
    kbd
    -0.25
    CCCC
    -0.25
    forth
    -0.25
    living
    -0.25
     enf
    -0.24
    POSITIVE LOGITS
     shape
    0.30
    å½¢çĬ¶
    0.29
     cong
    0.28
     shapes
    0.27
    å¡ijéĢł
    0.25
     straight
    0.25
    ç»Łè®¡æķ°æį®
    0.25
    shape
    0.25
     compensated
    0.25
    hape
    0.25
    Activations Density 0.910%

    No Known Activations