© 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. 56323
    Prev
    Next
    INDEX
    Explanations

    for a

    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
    ìĤ¼
    -0.12
    itel
    -0.10
    èĶ¬
    -0.09
    äºĴèģĶ
    -0.09
    åıĺåİĭ
    -0.09
    ohn
    -0.09
    endum
    -0.09
    oste
    -0.09
    åī¯
    -0.08
    æĭľå¸Ī
    -0.08
    POSITIVE LOGITS
    æĤĦçĦ¶
    0.11
    æĻ®
    0.11
    åīįçŀ»
    0.09
    棣
    0.08
    ä½łè¯´
    0.08
    etta
    0.08
    inese
    0.08
    ä¸įéĢļ
    0.08
    Bright
    0.08
    ä¸ĥåħ«
    0.08
    Activations Density 0.065%

    No Known Activations