© 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. 6459
    Prev
    Next
    INDEX
    Explanations

    acid or acids

    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¸Ģå¹ķ
    -0.09
    eer
    -0.08
    ä¸ĩäºĭ
    -0.08
    çļĦæĹ¥åŃIJéĩĮ
    -0.08
    istence
    -0.08
    åıĸè¯ģ
    -0.08
    幡
    -0.08
    举æĸ¹
    -0.08
    èŁ¾
    -0.08
    åį¡
    -0.08
    POSITIVE LOGITS
    auce
    0.10
    çĥĤ
    0.10
     ÑĦоÑĤогÑĢаÑĦ
    0.09
     Beste
    0.09
    åį·
    0.09
    樱æ¡ĥ
    0.09
    çIJ¢
    0.09
    peg
    0.09
    çŁ¿æ³īæ°´
    0.09
    funcs
    0.09
    Activations Density 0.112%

    No Known Activations