© 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. 97097
    Prev
    Next
    INDEX
    Explanations

    Questions, code and storage

    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
    enen
    -0.27
     spontaneously
    -0.26
    eria
    -0.25
     kone
    -0.25
    elen
    -0.24
    æ¯Ľ
    -0.24
    ,height
    -0.23
     drawn
    -0.23
     cheer
    -0.23
    è·»
    -0.23
    POSITIVE LOGITS
     away
    0.38
     Away
    0.33
    -away
    0.31
     rotating
    0.29
    Away
    0.28
     refriger
    0.27
     rotated
    0.27
    æĹĭ转
    0.27
    icle
    0.27
    Rotation
    0.27
    Activations Density 0.884%

    No Known Activations