© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23992
    Prev
    Next
    INDEX
    Explanations

    outspoken vocalism

    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
    ëĨĵ
    -0.08
    ç²ĴåŃIJ
    -0.08
    ç»ıåİĨ
    -0.08
    殿åłĤ
    -0.08
    ÑĤоп
    -0.08
    xcc
    -0.08
    å¯ĨåĪĩ
    -0.08
    æŶæŶ
    -0.08
    landers
    -0.08
    çħ§
    -0.08
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.12
    缸åĬ©
    0.11
    åĵij
    0.10
    éļľ
    0.09
    ely
    0.09
    ly
    0.09
    å°ijæķ°
    0.09
    ized
    0.09
     enough
    0.09
    æĬĵ好
    0.09
    Activations Density 0.007%

    No Known Activations