© 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. 33008
    Prev
    Next
    INDEX
    Explanations

    lives in geographical locations

    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
    驼
    -0.11
    æĮł
    -0.09
    éªĪ
    -0.09
     вÑħод
    -0.09
     Lyons
    -0.09
    jad
    -0.09
    Dot
    -0.08
    amine
    -0.08
    æĹłæķĪ
    -0.08
    ç¼Ĵ
    -0.08
    POSITIVE LOGITS
    NAL
    0.09
    åĦ¿
    0.08
    texts
    0.08
    åĪĩ
    0.08
    åĢ¡å¯¼
    0.08
    çļĦæĪ¿åŃIJ
    0.08
    fusion
    0.08
    åħĴ
    0.07
    çļĦæł·åŃIJ
    0.07
    _MM
    0.07
    Activations Density 0.084%

    No Known Activations