© 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. 37832
    Prev
    Next
    INDEX
    Explanations

    light bulbs and filaments

    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
    èģĮ
    -0.09
    åŃIJ
    -0.08
    ÙħÙĨت
    -0.08
    è´£
    -0.08
    VED
    -0.08
    aced
    -0.08
    -navigation
    -0.08
     Bounty
    -0.08
    -enter
    -0.08
    æ¶Ī
    -0.08
    POSITIVE LOGITS
    åĿ©
    0.11
    ç¬Ļ
    0.10
    åIJIJ
    0.10
    æģį
    0.09
    壮
    0.09
    çĨ
    0.09
    å¿ĥè¡Ģ
    0.09
    éķĿ
    0.09
    åĽŀæĥ³
    0.09
    ç§ijæķĻ
    0.09
    Activations Density 0.058%

    No Known Activations