© 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. 58314
    Prev
    Next
    INDEX
    Explanations

    need some help or advice

    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
    ç»ĻäºĨæĪij
    -0.11
    è¦ģæ±Ĥ
    -0.09
    è¦ģ害
    -0.09
    ç»ĻäºĨ
    -0.09
    æľªçŁ¥
    -0.08
    elic
    -0.08
     Drum
    -0.08
    ä¸Ģ天
    -0.08
    让æĪij
    -0.08
    æĭ¥æľī
    -0.08
    POSITIVE LOGITS
    æīįèĥ½
    0.14
    åģļçļĦäºĭæĥħ
    0.12
    lessly
    0.11
    æīįçŁ¥éģĵ
    0.11
    æīįä¼ļ
    0.11
    æīįå¹²
    0.11
    æīįèĥ½å¤Ł
    0.11
    è¿Ļæł·æīįèĥ½
    0.10
    åĨįåİ»
    0.10
     desperately
    0.10
    Activations Density 0.276%

    No Known Activations