© 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. 10295
    Prev
    Next
    INDEX
    Explanations

    some kind of

    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
     Raid
    -0.08
    llen
    -0.08
    NGTH
    -0.08
    åŃIJå¼Ł
    -0.08
     Banc
    -0.08
    å°ģ
    -0.08
    termin
    -0.08
    ög
    -0.08
    å®ŀæĪĺ
    -0.08
    çīµ
    -0.08
    POSITIVE LOGITS
    æŁIJç§į
    0.22
     somehow
    0.19
     somew
    0.18
    æŁIJç§įç¨ĭ度
    0.17
    æĪĸå¤ļæĪĸå°ij
    0.16
    ä»»ä½ķå½¢å¼ı
    0.15
     irgend
    0.13
    ä¸įåIJĮç¨ĭ度
    0.13
     alguna
    0.12
    äºĽä»Ģä¹Ī
    0.11
    Activations Density 0.163%

    No Known Activations