© 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. 40757
    Prev
    Next
    INDEX
    Explanations

    sat

    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
     hits
    -0.28
     recruits
    -0.27
     condition
    -0.27
     appointments
    -0.26
     appointment
    -0.26
     ops
    -0.26
     relev
    -0.26
     volley
    -0.26
     hit
    -0.25
     snaps
    -0.25
    POSITIVE LOGITS
    ieten
    0.34
    hra
    0.31
    ie
    0.29
    iw
    0.28
    rah
    0.28
    icit
    0.28
    nings
    0.28
    iei
    0.27
    ire
    0.27
    iah
    0.27
    Activations Density 0.197%

    No Known Activations