© 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. 27362
    Prev
    Next
    INDEX
    Explanations

    information handling and usage

    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
    æļ®
    -0.09
    acks
    -0.09
    igner
    -0.08
    åįĪé¥Ń
    -0.08
    éĺī
    -0.08
    åı¯è°ĵ
    -0.08
    enga
    -0.08
    åĨı
    -0.08
    apter
    -0.08
    å¸Ĥåİ¿
    -0.08
    POSITIVE LOGITS
    æĭ§
    0.09
    ä¸įåĩº
    0.09
    éĤ£ä½į
    0.09
    /by
    0.09
    berry
    0.09
    éĻ¤æѤ
    0.09
    骨干
    0.08
    æĿIJ
    0.08
    çıĪ
    0.08
     Clips
    0.08
    Activations Density 0.016%

    No Known Activations