© 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. 31-TRANSCODER-HP
    7. 17980
    Prev
    Next
    INDEX
    Explanations

    part

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    /spec
    -0.26
    .isOn
    -0.24
    atory
    -0.24
     remin
    -0.23
     scare
    -0.23
    vie
    -0.23
    åIJĪåĶ±
    -0.23
     coll
    -0.23
    -directed
    -0.23
    èķĪ
    -0.23
    POSITIVE LOGITS
     particle
    0.42
    é¢Ĺç²Ĵ
    0.40
     PARTIC
    0.39
     partic
    0.39
     Particle
    0.36
    ç²Ĵ
    0.35
    ç²ĴåŃIJ
    0.34
     particles
    0.34
    Particle
    0.32
    _particles
    0.32
    Activations Density 1.002%

    No Known Activations