© 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. 58838
    Prev
    Next
    INDEX
    Explanations

    sequel or continuation

    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
    anel
    -0.13
    æķĽ
    -0.10
    noc
    -0.09
    ANEL
    -0.08
     Bain
    -0.08
    æĹĭ
    -0.08
    Naz
    -0.08
     TOM
    -0.08
    jing
    -0.08
    /cms
    -0.08
    POSITIVE LOGITS
    ç»Ń
    0.13
     sequel
    0.12
    åIJİç»Ń
    0.12
     trilogy
    0.11
     successor
    0.11
    çºĮ
    0.11
    å¼ij
    0.10
     continuation
    0.09
    ç¥ĸ
    0.09
    æŁ³
    0.09
    Activations Density 0.136%

    No Known Activations