© 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. 40300
    Prev
    Next
    INDEX
    Explanations

    crisp qualities

    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
    Negative Logits
    erro
    -0.10
    æĸ°æĹ¶æľŁ
    -0.10
    psilon
    -0.09
     Hague
    -0.09
    ãĥķãĤ©ãĥ¼
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    æѤ
    -0.09
    รà¸ĸ
    -0.08
    _serialize
    -0.08
    abei
    -0.08
    POSITIVE LOGITS
    ingly
    0.15
    ness
    0.11
    ç¢į
    0.10
    iness
    0.10
    çĪ½
    0.10
    å¹²åĩĢ
    0.09
    èĥ½æī¾åĪ°
    0.09
    inator
    0.09
    ä½ľä¸ºä¸Ģ个
    0.09
    NESS
    0.09
    Activations Density 0.002%

    No Known Activations