© 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. 51323
    Prev
    Next
    INDEX
    Explanations

    past/last week or year

    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
    sus
    -0.09
    zej
    -0.08
    ç»ıèIJ¥æ´»åĬ¨
    -0.08
    çĽ¼
    -0.08
    HL
    -0.08
    éĤĽ
    -0.08
    享åıĹåĪ°
    -0.08
    æ®ĥ
    -0.08
    ffff
    -0.08
    Ha
    -0.08
    POSITIVE LOGITS
    éģĹ产
    0.11
    unas
    0.09
    èĸ®
    0.09
    é»Ħæĺı
    0.09
    åľī
    0.09
    ÑĢаз
    0.08
    ä¸įæĸŃæī©å¤§
    0.08
    BIND
    0.08
    forme
    0.08
    å¯Ĩçłģ
    0.08
    Activations Density 0.072%

    No Known Activations