© 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. 31654
    Prev
    Next
    INDEX
    Explanations

    grams_list, shelv, whisper, sunday, story

    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
    ewriter
    -0.10
    akedown
    -0.09
    æij¸
    -0.09
    离
    -0.09
    ä½ĵ彩
    -0.09
    rts
    -0.09
     Cookies
    -0.09
    è§Ĩ
    -0.09
    éĽķ
    -0.09
    lage
    -0.08
    POSITIVE LOGITS
    社ä¼ļåĮĸ
    0.10
     anonymously
    0.10
    社交
    0.08
    è´«
    0.08
    æĢ¦
    0.08
    æĺ¯éĿŀ
    0.08
    æ³Ħ
    0.08
    åķª
    0.08
    æķŀå¼Ģ
    0.08
    éļıå¤Ħ
    0.08
    Activations Density 0.142%

    No Known Activations