© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4754
    Prev
    Next
    INDEX
    Explanations

    taking risks

    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
    oop
    -0.10
    å®ŀåľ¨
    -0.09
    itra
    -0.09
    åĪ°ä½į
    -0.09
    hem
    -0.09
    èijī
    -0.09
    ä½łèĩªå·±
    -0.09
    iasco
    -0.08
    æµĵ
    -0.08
    Logged
    -0.08
    POSITIVE LOGITS
    ä¸ĢéĶ®
    0.08
     bold
    0.08
    ç»ijæŀ¶
    0.08
    Ñıми
    0.08
    åľ¨æĪijçľĭæĿ¥
    0.08
    èĽ®
    0.08
    eson
    0.08
    ÙĪبر
    0.08
    uler
    0.08
    ForMember
    0.08
    Activations Density 0.011%

    No Known Activations