© 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. 21135
    Prev
    Next
    INDEX
    Explanations

    radio stations and frequencies

    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
    ç´łæĿIJ
    -0.10
    arkin
    -0.09
     CRE
    -0.09
    æ¬
    -0.09
    é¢Ħæ¡Ī
    -0.09
    裸
    -0.09
    åĴ¬
    -0.08
    è¿ĽäºĨ
    -0.08
    å²Ĺ
    -0.08
    oub
    -0.08
    POSITIVE LOGITS
    ä¹ĭåĬ¿
    0.10
    ervers
    0.09
     Recon
    0.09
    éĹ®éģĵ
    0.09
    è´¼
    0.09
    æ¶Ĥ
    0.09
    ä¸Ĭæľī
    0.08
     radio
    0.08
    è´Ńçī©
    0.08
    é¢ijçİĩ
    0.08
    Activations Density 0.151%

    No Known Activations