© 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. 62597
    Prev
    Next
    INDEX
    Explanations

    Sacramento and related words

    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
    çłľ
    -0.10
    cott
    -0.09
    од
    -0.09
     ÙħØŃÙĦ
    -0.08
    ie
    -0.08
    odor
    -0.08
    ÑĢÑĥÑĩ
    -0.08
    inks
    -0.08
    æľ¬ç½ij
    -0.08
    çģ¾éļ¾
    -0.08
    POSITIVE LOGITS
    enzie
    0.10
    lesi
    0.10
    SES
    0.10
    ramento
    0.09
    reeNode
    0.09
    atel
    0.09
     Bundy
    0.09
    诡
    0.08
    ellular
    0.08
    eer
    0.08
    Activations Density 0.026%

    No Known Activations