© 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. 10416
    Prev
    Next
    INDEX
    Explanations

    center, 0, , the, hello, tolerance, ., enny

    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
    icer
    -0.09
    è¶ħé¢Ŀ
    -0.08
     Lore
    -0.08
    èŤ
    -0.08
    èIJ§
    -0.08
    èĩªçIJĨ
    -0.08
    hin
    -0.08
    ç»ĨåĮĸ
    -0.08
    è·ij
    -0.08
    arter
    -0.07
    POSITIVE LOGITS
    æķĻèĤ²èµĦæºIJ
    0.13
    ç§ijæĻ®
    0.12
    åįļçī©é¦Ĩ
    0.12
    å¯ĵ
    0.11
    å±ķåĵģ
    0.11
    åįļçī©
    0.11
    æķĻèĤ²
    0.11
    éĿĴå°ijå¹´
    0.10
    çİ©åħ·
    0.10
    对åŃ©åŃIJ
    0.10
    Activations Density 0.090%

    No Known Activations