© 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. 3052
    Prev
    Next
    INDEX
    Explanations

    "in" followed by location

    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
    omes
    -0.10
    åįģä¸īå±Ĭ
    -0.09
    ansson
    -0.09
    еÐ
    -0.08
    çİĭåĽ½
    -0.08
    aska
    -0.08
    娱ä¹IJå¹³åı°
    -0.08
    lems
    -0.08
    eam
    -0.08
    ä¸»åľº
    -0.08
    POSITIVE LOGITS
    æ¶ī
    0.10
    樵
    0.09
    å«Įçĸij人
    0.09
    ãĥĭãĥ¼
    0.09
    пл
    0.08
    èĻij
    0.08
    大ä¼Ĺ
    0.08
    éĹ¹
    0.08
    èĢĺ
    0.08
    ä¸īåĽĽ
    0.08
    Activations Density 0.191%

    No Known Activations