© 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. 20205
    Prev
    Next
    INDEX
    Explanations

    might want, may have

    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»ĻåĪ«äºº
    -0.11
    ç»Ļä½łä»¬
    -0.09
    å¸¦ä½ł
    -0.09
    ï¸
    -0.09
    è¹Ń
    -0.09
    è·Łä½ł
    -0.09
    tsy
    -0.08
    éĿłè°±
    -0.08
    æĢİä¹Īåı¯èĥ½
    -0.08
    junction
    -0.08
    POSITIVE LOGITS
    æĦŁåĪ°
    0.14
    éľĢè¦ģçĶ¨
    0.13
    è§īå¾Ĺ
    0.12
    æĦŁè§īåĪ°
    0.11
    æĦıè¯ĨåĪ°
    0.11
    æĶ¾å¿ĥ
    0.10
    éģĩåĪ°äºĨ
    0.10
    çĸijéĹ®
    0.10
    覺å¾Ĺ
    0.10
     wondering
    0.10
    Activations Density 0.052%

    No Known Activations