© 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. 19273
    Prev
    Next
    INDEX
    Explanations

    fabulous descriptors

    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
    /OR
    -0.10
    lessly
    -0.10
    å°´å°¬
    -0.09
    åıijå±ķè§ĦåĪĴ
    -0.09
    ÙĨ
    -0.08
    /she
    -0.08
    /or
    -0.08
    çļĦç¾İ好
    -0.08
    /rem
    -0.08
    æ¯Ķè¾ĥç®Ģåįķ
    -0.08
    POSITIVE LOGITS
    ness
    0.15
    ulously
    0.10
    ä¸İåIJ¦
    0.09
    ity
    0.09
     Serg
    0.09
    NESS
    0.09
    ç¿Ł
    0.09
    ifer
    0.09
    egin
    0.09
    ishment
    0.09
    Activations Density 0.003%

    No Known Activations