© 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. 38601
    Prev
    Next
    INDEX
    Explanations

    view of

    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
    ä¿¡æģ¯åıijå¸ĥ
    -0.09
    ducer
    -0.09
    åįĬ天
    -0.08
     darkness
    -0.08
    ql
    -0.08
    äºĭå®ŀä¸Ĭ
    -0.08
    æĻĤ代
    -0.08
    oud
    -0.08
    ument
    -0.08
    RetVal
    -0.07
    POSITIVE LOGITS
    Requested
    0.09
    tur
    0.09
    åħ¨éĿ¢èIJ½å®ŀ
    0.09
    panse
    0.09
    å¦ĸ
    0.09
     паÑĢÑĤ
    0.09
    èĨº
    0.08
     purse
    0.08
    èĤ©
    0.08
    è²Į
    0.08
    Activations Density 0.031%

    No Known Activations