© 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. 19825
    Prev
    Next
    INDEX
    Explanations

    academic text

    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
    scal
    -0.29
    crew
    -0.28
    conte
    -0.26
     matte
    -0.24
    cona
    -0.24
     cooler
    -0.24
    cade
    -0.23
    sembl
    -0.23
     slack
    -0.23
     Fayette
    -0.23
    POSITIVE LOGITS
    agal
    0.30
    din
    0.29
    红
    0.28
    ansa
    0.28
    åİĭ
    0.27
    anging
    0.26
    iban
    0.26
    åį±éĻ©
    0.26
    æĮ¯
    0.25
    ogan
    0.25
    Activations Density 0.005%

    No Known Activations