© 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. 48128
    Prev
    Next
    INDEX
    Explanations

    for once

    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
     ÑģпÑĢав
    -0.09
    ä¸Ģå¹ķ
    -0.08
    å¿ħ
    -0.08
    åĬłæ²¹
    -0.08
    neo
    -0.08
     ÑįÑĤим
    -0.08
    atee
    -0.08
    aut
    -0.07
    uration
    -0.07
    ëį°
    -0.07
    POSITIVE LOGITS
    çŀ»
    0.10
    æݪ
    0.10
     Dexter
    0.10
    åĴĮæĶ¯æĮģ
    0.10
    å®ŀå®ŀåľ¨åľ¨
    0.09
    æĿŀ
    0.09
     bey
    0.09
    æ´ģçĻ½
    0.09
    ä¸įåĨį
    0.09
    ç½ķè§ģ
    0.09
    Activations Density 0.036%

    No Known Activations