© 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. 62341
    Prev
    Next
    INDEX
    Explanations

    tribes and nations

    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
    obo
    -0.09
    åļ¼
    -0.09
    çĺ«
    -0.09
    æıŃ
    -0.09
    æĮĩå¼ķ
    -0.08
    ä¸į幸
    -0.08
    èĬ±èįī
    -0.08
     arch
    -0.08
    èijµ
    -0.08
     Modular
    -0.08
    POSITIVE LOGITS
    满æĦıçļĦ
    0.09
    Ľå»º
    0.09
    -owned
    0.09
    æĸ°ä¸ĸ纪
    0.09
    为主ä½ĵ
    0.09
    insk
    0.08
    èĪī
    0.08
    OfWork
    0.08
    享
    0.08
     üyeler
    0.08
    Activations Density 0.034%

    No Known Activations