© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6401
    Prev
    Next
    INDEX
    Explanations

    band wagon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    athing
    -0.09
    åºŃ
    -0.09
    yz
    -0.08
    ilton
    -0.08
    elib
    -0.08
     physic
    -0.08
    æ¯ıå½ĵ
    -0.08
    æĿ¥çĶµ
    -0.08
     PSI
    -0.08
     metic
    -0.08
    POSITIVE LOGITS
     band
    0.12
     banda
    0.11
     bands
    0.11
    Band
    0.11
    bands
    0.11
     Band
    0.11
    band
    0.11
     Bands
    0.11
    -band
    0.10
    èµı
    0.10
    Activations Density 0.018%

    No Known Activations