© 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. 57572
    Prev
    Next
    INDEX
    Explanations

    question / answer

    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
    çļĭ
    -0.09
    对çħ§
    -0.09
    åĻ¢
    -0.09
    åģľçĶµ
    -0.09
    ä¿ij
    -0.08
     Spell
    -0.08
    amin
    -0.08
    ä¿¡æģ¯åıijå¸ĥ
    -0.08
    ÙĦازÙħ
    -0.08
    hausen
    -0.08
    POSITIVE LOGITS
    é¢ĺ主
    0.09
    è´¡
    0.09
     Vig
    0.08
    请éĹ®
    0.08
     yabancı
    0.08
    eren
    0.08
    åĪ¹éĤ£
    0.08
    ashes
    0.08
    hawk
    0.08
    诱
    0.08
    Activations Density 6.727%

    No Known Activations