© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20033
    Prev
    Next
    INDEX
    Explanations

    short phrases asking questions or making statements

    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
    visit
    -0.09
    .partition
    -0.08
    zi
    -0.07
    ÙĨÙĪ
    -0.07
    è°ĥåīĤ
    -0.07
    onom
    -0.07
     seam
    -0.07
     ìĭľíĸī
    -0.07
     spontaneously
    -0.07
    åĿĬ
    -0.07
    POSITIVE LOGITS
    ç²¾åĬĽ
    0.10
    olib
    0.09
    çĴľ
    0.09
    åħ¶ä»ĸ人
    0.09
    éĢĤ
    0.09
    æ½
    0.08
    ç¨Ķ
    0.08
    诱
    0.08
    群éĩĮ
    0.08
    çļĦèĦļæŃ¥
    0.08
    Activations Density 0.228%

    No Known Activations