© 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. 52396
    Prev
    Next
    INDEX
    Explanations

    as a whole

    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
     sop
    -0.09
    æĬ¢æķij
    -0.08
    iew
    -0.08
    æ·ħ
    -0.08
    亲
    -0.08
    ä¸įå¦Ĥ
    -0.08
    -times
    -0.08
    ÙĬÙĩ
    -0.08
    çļĩ家
    -0.08
    indo
    -0.08
    POSITIVE LOGITS
    æķ´ä½ĵ
    0.28
    çļĦæķ´ä½ĵ
    0.22
    æĢ»ä½ĵ
    0.18
     overall
    0.17
    åħ¨ä½ĵ
    0.17
     Overall
    0.16
    Overall
    0.16
     whole
    0.16
    overall
    0.15
     entirety
    0.15
    Activations Density 0.046%

    No Known Activations