© 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. 40787
    Prev
    Next
    INDEX
    Explanations

    ich

    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
    带æĿ¥
    -0.26
    desired
    -0.26
     tease
    -0.25
     holders
    -0.24
     essentials
    -0.24
    REATE
    -0.24
     haste
    -0.24
    Retention
    -0.23
     tweaked
    -0.23
    èµŀç¾İ
    -0.23
    POSITIVE LOGITS
    icit
    0.40
    ocy
    0.38
    ich
    0.36
    icol
    0.35
    iac
    0.35
    ovic
    0.35
    ific
    0.35
    ico
    0.34
    icz
    0.34
    icio
    0.34
    Activations Density 13.003%

    No Known Activations