© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29700
    Prev
    Next
    INDEX
    Explanations

    lexical entries

    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
    ingly
    -0.11
    ðŁı»
    -0.09
    sWith
    -0.09
     lÆ°ng
    -0.09
    -thirds
    -0.08
    stellung
    -0.08
    æľ¨èĢ³
    -0.08
    leurs
    -0.08
    agement
    -0.07
    abouts
    -0.07
    POSITIVE LOGITS
    讼
    0.11
    èľ´
    0.10
    ä¸įæ¸ħ
    0.09
    á»ĩn
    0.09
    妤
    0.09
    lection
    0.09
    åѤåĦ¿
    0.09
    æ¸ħæ¥ļ
    0.09
    å¾Ģå¤ĸ
    0.09
    quip
    0.09
    Activations Density 0.011%

    No Known Activations