© 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. 64033
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    å°±æѤ
    -0.10
    çĭIJ
    -0.10
    仵
    -0.09
    anche
    -0.09
    寰
    -0.09
    à¹Ĩ
    -0.09
    磼
    -0.08
    å²Ĺ
    -0.08
    æķĻèĤ²æķĻåѦ
    -0.08
    że
    -0.08
    POSITIVE LOGITS
    èĢģå¸ĪçļĦ
    0.09
    æĪij们è¦ģ
    0.08
     pomp
    0.08
    repos
    0.08
    Accordion
    0.08
    è¦ģæĬĬ
    0.08
    Spo
    0.08
    èłĭ
    0.07
    åĪ«
    0.07
    è®°
    0.07
    Activations Density 0.037%

    No Known Activations