© 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. 6602
    Prev
    Next
    INDEX
    Explanations

    records books and roll

    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
    ói
    -0.09
    æĹ¥è®°
    -0.09
    adena
    -0.09
    Fa
    -0.08
    AspNet
    -0.08
    è¿ĩæķı
    -0.08
     обÑĭ
    -0.08
    atat
    -0.08
    åĦ²
    -0.08
    oco
    -0.08
    POSITIVE LOGITS
    ä»ij
    0.09
     Warwick
    0.09
    ots
    0.09
    åĿĿ
    0.08
    lobe
    0.08
     gratuit
    0.08
    zelf
    0.08
    ä½įäºİ
    0.08
    est
    0.08
    icie
    0.08
    Activations Density 0.003%

    No Known Activations