© 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. 39586
    Prev
    Next
    INDEX
    Explanations

    buckle and fasteners

    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
    媳
    -0.10
    strate
    -0.09
    èĹ
    -0.08
    æĶ¹åĪ¶
    -0.08
     baseman
    -0.08
    places
    -0.08
    ilege
    -0.08
    å§Ķå®£ä¼łéĥ¨
    -0.08
    åĿª
    -0.08
    bery
    -0.08
    POSITIVE LOGITS
    eg
    0.09
    ä¸įä¸Ĭ
    0.08
    stry
    0.08
    æĢ¨
    0.08
    eil
    0.08
    KE
    0.08
    æ±
    0.08
    åĢĴåľ¨åľ°
    0.08
    _strike
    0.08
     Cousins
    0.08
    Activations Density 0.007%

    No Known Activations