© 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. 9626
    Prev
    Next
    INDEX
    Explanations

    issue resolution

    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
    è¿Ļä¸ĢçĤ¹
    -0.09
    è¾Ľ
    -0.08
    çĵľ
    -0.08
    /download
    -0.08
     зан
    -0.08
    conditionally
    -0.08
    osis
    -0.08
     vivid
    -0.08
    èĤĩ
    -0.08
    æĿ¡ä»¶
    -0.08
    POSITIVE LOGITS
    解åĨ³
    0.18
    解決
    0.15
    å¤ĦçIJĨ
    0.15
     íķ´ê²°
    0.14
     resolution
    0.14
    解åĨ³äºĨ
    0.14
    妥
    0.13
    妥åĸĦ
    0.12
    èĻķçIJĨ
    0.12
    Resolution
    0.12
    Activations Density 0.079%

    No Known Activations