© 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. 41121
    Prev
    Next
    INDEX
    Explanations

    the ending -ing

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĪijéĥ½
    -0.35
     HAVE
    -0.35
     have
    -0.34
     têm
    -0.34
    éĥ½æľī
    -0.34
     são
    -0.34
    've
    -0.34
    éĥ½è®¤ä¸º
    -0.32
    éĥ½æĺ¯
    -0.32
    have
    -0.31
    POSITIVE LOGITS
     works
    0.41
     produces
    0.31
    æĺ¯éĿŀ
    0.30
     your
    0.29
     appears
    0.29
    your
    0.29
    works
    0.28
     Works
    0.28
     could
    0.28
     is
    0.28
    Activations Density 0.003%

    No Known Activations