© 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. 61359
    Prev
    Next
    INDEX
    Explanations

    some kind of

    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
     somewhat
    -0.09
    anes
    -0.09
    dÃŃ
    -0.08
    edly
    -0.08
    ather
    -0.08
    åı¯èĥ½æĢ§
    -0.08
    teen
    -0.08
    nee
    -0.08
    ä½ĵä¼ļåĪ°
    -0.08
     tote
    -0.08
    POSITIVE LOGITS
    æŶåĢĻ
    0.11
    place
    0.11
    ç»
    0.11
    åĩłåįĥ
    0.10
    æĻĤåĢĻ
    0.10
    ÅĽl
    0.10
    æĹ¥åŃIJ
    0.10
    ä¸Ģæīĭ
    0.10
    åĶ¿
    0.10
    ç¬
    0.09
    Activations Density 0.059%

    No Known Activations