© 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. 1755
    Prev
    Next
    INDEX
    Explanations

    starting new ventures

    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
    зна
    -0.09
    å±ķä½į
    -0.09
     án
    -0.08
    åħ¥å¢ĥ
    -0.08
    èµĵ
    -0.08
    CAS
    -0.08
    åįļè§Ī
    -0.08
    éļĨ
    -0.08
    è¯ģåĪ¸äº¤æĺĵ
    -0.08
    趱
    -0.08
    POSITIVE LOGITS
    èĩªå·±çļĦ
    0.12
    çĽij
    0.12
    æĪIJç«ĭ
    0.12
    äºĨèĩªå·±çļĦ
    0.10
    åIJĪèµĦåħ¬åı¸
    0.10
    .twig
    0.09
    OWN
    0.09
     Own
    0.09
    èĩªæĿ¥
    0.09
    åĪĽç«ĭ
    0.09
    Activations Density 0.108%

    No Known Activations