© 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. 38590
    Prev
    Next
    INDEX
    Explanations

    dried things

    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
    offs
    -0.10
    shine
    -0.09
    antium
    -0.09
    nik
    -0.09
    بÙĪت
    -0.09
    uating
    -0.09
    kaar
    -0.09
    ëĿ½
    -0.08
    ÙħÙĬØ©
    -0.08
    MENTS
    -0.08
    POSITIVE LOGITS
    å¤ĩ
    0.10
    æ¦
    0.09
    æĶ¶æķĽ
    0.09
    大åħ¨
    0.09
     Belly
    0.09
     Sage
    0.09
    æĥ³å¿µ
    0.09
    éļ½
    0.09
    ideal
    0.08
    owell
    0.08
    Activations Density 0.018%

    No Known Activations