© 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. 27638
    Prev
    Next
    INDEX
    Explanations

    periods, Condition, autocomplete

    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
    éª
    -0.09
    è¿Ļæł·ä¸Ģ个
    -0.09
    ubits
    -0.09
    åĮħåĮħ
    -0.09
    ç¬ijçĿĢ
    -0.09
     Rehab
    -0.09
    ä¸įæ¸ħ
    -0.09
    technology
    -0.09
    -eng
    -0.08
    Presence
    -0.08
    POSITIVE LOGITS
    åħħ足
    0.12
    åħīçħ§
    0.11
    足
    0.11
    åħħ足çļĦ
    0.10
    çĿ¡çľł
    0.10
     sleep
    0.10
    åħħæ²Ľ
    0.09
     Sleep
    0.09
    åı°
    0.09
    æ°´éĩı
    0.08
    Activations Density 0.192%

    No Known Activations