© 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. 4283
    Prev
    Next
    INDEX
    Explanations

    though but

    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
    好åIJĹ
    -0.11
    éļ¾éģĵ
    -0.10
    åĴķ
    -0.10
    ä¹ĭ乡
    -0.09
    è¿Ļ群
    -0.09
    ä¸įäºĨ
    -0.09
    stor
    -0.09
    èĢĮä¸Ķè¿ĺ
    -0.09
    æ£Ģçĸ«
    -0.09
    çļ¿
    -0.09
    POSITIVE LOGITS
    ness
    0.10
    iness
    0.09
    out
    0.09
    ÑīÑĥ
    0.09
    irmed
    0.09
     shalt
    0.09
    sis
    0.09
    ousel
    0.09
    ascal
    0.09
    èĩ¾
    0.09
    Activations Density 0.016%

    No Known Activations