© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36910
    Prev
    Next
    INDEX
    Explanations

    zimbabwe

    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
    bout
    -0.10
    ä¹İ
    -0.09
    ä¸ŃåĽ½åĽ½éĻħ
    -0.09
    ition
    -0.09
    ä¸ŃåĽ½å¸Ĥåľº
    -0.08
    ä¿¡æģ¯æľįåĬ¡
    -0.08
    æ¸Ŀ
    -0.08
    terra
    -0.08
    rum
    -0.08
    MAND
    -0.08
    POSITIVE LOGITS
    çĽİ
    0.10
    леÑĩ
    0.10
    ÙĬÙĪÙĨ
    0.10
    Úº
    0.09
    .webkit
    0.09
    æĥ°
    0.09
    ENCE
    0.09
    atory
    0.09
     bore
    0.09
    ers
    0.09
    Activations Density 0.007%

    No Known Activations