© 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. 32-TRANSCODER-HP
    7. 43962
    Prev
    Next
    INDEX
    Explanations

    oct

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸Ŀ
    -0.30
    ificent
    -0.27
    Ent
    -0.26
    анÑģ
    -0.24
    Pix
    -0.24
     Singleton
    -0.24
    çݯ
    -0.24
    atab
    -0.23
    anel
    -0.23
     coeff
    -0.23
    POSITIVE LOGITS
     oct
    0.32
    oct
    0.31
     sez
    0.27
    éģĤ
    0.27
    åİ¥
    0.25
    urement
    0.25
    -Oct
    0.25
    ::::::
    0.25
     Oct
    0.25
    Oct
    0.24
    Activations Density 0.005%

    No Known Activations