© 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. 54577
    Prev
    Next
    INDEX
    Explanations

    don't have / need / find

    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
    æĹłæķ°æ¬¡
    -0.11
    å¦Ĥæŀľä¸įæĺ¯
    -0.09
    对å¾ħ
    -0.09
    åĶ¯ä¸ĢçļĦ
    -0.09
    æĨĶ
    -0.09
    ponge
    -0.09
    æľĢéĩįè¦ģçļĦ
    -0.09
    AGO
    -0.09
    ä¸įä¸Ģæł·çļĦ
    -0.09
    æľĢé«ĺçļĦ
    -0.09
    POSITIVE LOGITS
    çļĦè¯Ŀ
    0.11
    çī¹åĪ«å£°æĺİ
    0.09
    å®ŀåĬĽ
    0.09
    è¿Ļä¹Īåģļ
    0.08
    è¿Ļæł·çļĦè¯Ŀ
    0.08
    è°Ļ
    0.08
    éĢī
    0.08
    çĨŁæĤī
    0.08
    æīİ
    0.08
    ëĿ¼ë©´
    0.08
    Activations Density 0.044%

    No Known Activations