© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21750
    Prev
    Next
    INDEX
    Explanations

    track surfaces

    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
    æı½
    -0.10
    æIJĤ
    -0.08
    çļĦçĶ»éĿ¢
    -0.08
    ONG
    -0.08
    人éĢī
    -0.08
    é¢Ĩ
    -0.08
    _Dep
    -0.08
     Rupert
    -0.08
    reich
    -0.08
     Ramos
    -0.08
    POSITIVE LOGITS
    å¹³æķ´
    0.14
    è·¯éĿ¢
    0.14
    车éģĵ
    0.13
    åľºåľ°
    0.13
    éĵºè®¾
    0.12
     lane
    0.11
    åľ°éĿ¢
    0.11
     lanes
    0.11
    æĴĴ
    0.11
    åľºæīĢ
    0.11
    Activations Density 0.096%

    No Known Activations