© 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. 39491
    Prev
    Next
    INDEX
    Explanations

    URLs ending in .com or .gl

    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
     crossword
    -0.08
    ych
    -0.08
    èĤ¯
    -0.08
    ำ
    -0.08
    RING
    -0.08
    éĺģ
    -0.08
    OID
    -0.07
     Cann
    -0.07
    纯
    -0.07
    æ±
    -0.07
    POSITIVE LOGITS
    ä¸Ģæ³¢
    0.11
    æłª
    0.10
    åıĮåIJij
    0.10
    éĶĻè¿ĩ
    0.09
    æ¹¾åĮº
    0.08
     Akron
    0.08
     Georges
    0.08
    åĻİ
    0.08
    çĽijçĿ£æ£ĢæŁ¥
    0.08
    ราย
    0.08
    Activations Density 0.098%

    No Known Activations