© 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. 18644
    Prev
    Next
    INDEX
    Explanations

    city names

    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
    è¢ħ
    -0.10
    åļ¼
    -0.10
    isu
    -0.09
    èī²æ³½
    -0.09
    ny
    -0.09
    éĢĴ
    -0.09
    åĦ¿
    -0.09
    WebHost
    -0.08
    åĸĭ
    -0.08
    eka
    -0.08
    POSITIVE LOGITS
    ä¿Ŀå®ī
    0.10
    ä¸Ģæ³¢
    0.10
    åīįæīĢ
    0.09
    amac
    0.09
    ixin
    0.09
    èľĪ
    0.09
    éĢĶ
    0.09
     OVERRIDE
    0.08
    å¿ĥçIJĨåĴ¨è¯¢
    0.08
    ohen
    0.08
    Activations Density 0.009%

    No Known Activations