© 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. 57609
    Prev
    Next
    INDEX
    Explanations

    patent numbers

    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
    ars
    -0.09
    arges
    -0.08
    å¸Ń
    -0.08
    eco
    -0.08
    麻
    -0.08
    滥
    -0.08
    INS
    -0.07
     Giants
    -0.07
     Pir
    -0.07
    thesis
    -0.07
    POSITIVE LOGITS
    æįī
    0.09
    å¤¸å¼ł
    0.09
    cestor
    0.09
    iker
    0.09
    оÑĢо
    0.09
    æ²¾
    0.09
    èģĶè°Ĭ
    0.09
    å¨ģæħij
    0.09
    é£İæĻ¯åĮº
    0.09
    éĵĽ
    0.09
    Activations Density 0.171%

    No Known Activations