© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38010
    Prev
    Next
    INDEX
    Explanations

    subscribe to updates

    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
    abal
    -0.10
    éĢı
    -0.10
    å¼ĢåıijåĮº
    -0.09
    éĢĬ
    -0.09
    é²·
    -0.09
    PMC
    -0.09
    _BUFF
    -0.09
    æĭIJ
    -0.08
    åĬŁå¤«
    -0.08
    ода
    -0.08
    POSITIVE LOGITS
     newsletter
    0.10
     newsletters
    0.09
     Newsletter
    0.09
    解æĶ¾æĢĿæĥ³
    0.09
    æ¸ħæ·¡
    0.08
    emit
    0.08
    antics
    0.08
    Subscribe
    0.08
    缴è¨Ģ
    0.08
     subscribe
    0.08
    Activations Density 0.044%

    No Known Activations