© 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. 4332
    Prev
    Next
    INDEX
    Explanations

    English historical figures

    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
    äºĮ线
    -0.10
    æĹłç¼Ŀ
    -0.09
    bate
    -0.09
    åĩĿèģļ
    -0.09
    åĢ¾
    -0.09
    èĢĮåĩº
    -0.09
    perate
    -0.09
    èĬ±èįī
    -0.08
    _goals
    -0.08
    utan
    -0.08
    POSITIVE LOGITS
    rels
    0.10
    éĿ©åij½
    0.10
    OSC
    0.10
    ä¼ĺ
    0.09
    èĤ¡ä¸ľ
    0.09
    éļ¼
    0.09
    è£Ļ
    0.09
    rd
    0.09
    ero
    0.09
    tsx
    0.09
    Activations Density 0.056%

    No Known Activations