© 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. 55632
    Prev
    Next
    INDEX
    Explanations

    meet with

    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
    artz
    -0.09
    èij¬
    -0.08
    èĩĤ
    -0.08
    ä¾ĭè¡Į
    -0.08
    æĪijä¸į
    -0.08
    arium
    -0.08
    åľ¨æĪijçļĦ
    -0.08
     ÑģебÑı
    -0.08
    åľ¨æĪij
    -0.08
    aget
    -0.08
    POSITIVE LOGITS
    åĨħéĺģ
    0.09
    ÑĢоÑĪ
    0.09
    ç¬ijç¬ij
    0.09
    ä¼ļè§ģ
    0.09
     Bow
    0.09
    åIJĦç§į
    0.09
    è£ķ
    0.09
     милли
    0.08
    abin
    0.08
     legit
    0.08
    Activations Density 0.053%

    No Known Activations