© 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. 1270
    Prev
    Next
    INDEX
    Explanations

    audio system components

    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
    imers
    -0.09
    icide
    -0.09
    ä¿Ŀåį«
    -0.08
     tess
    -0.08
    inded
    -0.08
    交代
    -0.08
    جاز
    -0.08
     TILE
    -0.08
    æ½Ń
    -0.08
    -short
    -0.08
    POSITIVE LOGITS
    大åıij
    0.11
    ä»ĸ认为
    0.10
    åįĴ
    0.09
     reprodu
    0.09
    èĩªé©¾
    0.09
    æĸ«
    0.09
    èĮ¶
    0.09
    ç»ıåħ¸çļĦ
    0.08
    æ¯ıæ¯ı
    0.08
    åĪĨ离
    0.08
    Activations Density 0.047%

    No Known Activations