© 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. 32630
    Prev
    Next
    INDEX
    Explanations

    cascade, chain, reaction

    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
    ç¼ij
    -0.09
    olas
    -0.09
    袤
    -0.09
    éļıæŶ
    -0.09
    æŶæŶ
    -0.08
    åĨ³èĥľ
    -0.08
    íħĶ
    -0.08
    åIJ¬å¾Ĺ
    -0.08
    åı¯ä»¥è¯´
    -0.08
    ingham
    -0.08
    POSITIVE LOGITS
    éĵ¾æĿ¡
    0.19
    è¿ŀéĶģ
    0.19
     cascade
    0.17
    éĵ¾
    0.17
     chain
    0.17
    cascade
    0.16
    chain
    0.15
    .chain
    0.15
    -chain
    0.15
    æķĪåºĶ
    0.15
    Activations Density 0.137%

    No Known Activations