© 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. 26385
    Prev
    Next
    INDEX
    Explanations

    on record, of choice

    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
    ç£IJ
    -0.09
     Inspiration
    -0.08
     inspired
    -0.08
     schl
    -0.08
     Insp
    -0.08
     Raised
    -0.08
     inspiration
    -0.08
     Sylv
    -0.08
    Icons
    -0.07
    åij³
    -0.07
    POSITIVE LOGITS
     record
    0.16
    è®°å½ķ
    0.15
    纪å½ķ
    0.14
     records
    0.13
     Record
    0.12
    record
    0.12
    èµĦæĸĻæĺ¾ç¤º
    0.12
    è¨ĺéĮĦ
    0.12
    è®°è½½
    0.12
    	record
    0.11
    Activations Density 0.111%

    No Known Activations