© 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. 56674
    Prev
    Next
    INDEX
    Explanations

    proposed settlement, arrangement, changes

    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
    .sleep
    -0.09
     sublist
    -0.09
    ãģŀ
    -0.09
    èĻ
    -0.09
    åŁķ
    -0.09
    обÑĢаÐ
    -0.08
    çĽ¸ä¿¡
    -0.08
    horn
    -0.08
    زÙĦ
    -0.08
    thest
    -0.08
    POSITIVE LOGITS
    渺
    0.13
    ively
    0.10
    çľĩ
    0.09
    สรร
    0.09
    ly
    0.09
    ive
    0.09
    éĵ²
    0.08
    涧
    0.08
    å·²ä¹ħ
    0.08
    æĭŁ
    0.08
    Activations Density 0.018%

    No Known Activations