© 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. 35-TRANSCODER-HP
    7. 38540
    Prev
    Next
    INDEX
    Explanations

    pen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     brav
    -0.24
     overriding
    -0.24
     зÑĢ
    -0.23
    ä¸ļæĢģ
    -0.23
     backwards
    -0.23
    ted
    -0.23
    çĶŁåij½åij¨æľŁ
    -0.22
    æ¸Ĺ
    -0.22
     subscribers
    -0.22
     Overs
    -0.22
    POSITIVE LOGITS
    ine
    0.38
    icine
    0.36
    ney
    0.35
    lace
    0.35
    ascus
    0.35
    iden
    0.34
    getic
    0.33
    ifix
    0.33
    pe
    0.33
    chine
    0.32
    Activations Density 0.013%

    No Known Activations