© 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. 50370
    Prev
    Next
    INDEX
    Explanations

    each/every year/day

    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
    æĩĪ
    -0.09
    ìŀ¬
    -0.09
    æĥ®
    -0.08
    lover
    -0.08
    èĢĮéĿŀ
    -0.08
    aks
    -0.08
    _HOR
    -0.08
    ë²
    -0.08
    ait
    -0.08
    rowse
    -0.07
    POSITIVE LOGITS
    æŶéĹ´åĴĮ
    0.11
    hir
    0.09
    iful
    0.09
    ÙĪÙĨØ©
    0.09
    oreach
    0.09
     деÑĤÑģк
    0.09
    fully
    0.08
    èħ°
    0.08
    pectrum
    0.08
    ç¨İåĬ¡å±Ģ
    0.08
    Activations Density 0.014%

    No Known Activations