© 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. 33632
    Prev
    Next
    INDEX
    Explanations

    court / locale

    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
    odi
    -0.09
    rollo
    -0.09
    valuate
    -0.09
    ocrat
    -0.08
    çļĦåij³éģĵ
    -0.08
    Las
    -0.08
     Las
    -0.08
    BuilderInterface
    -0.08
    åıĸ
    -0.08
    inz
    -0.08
    POSITIVE LOGITS
    éĩijåŃĹ
    0.11
    åĪĴ
    0.09
    enity
    0.09
    éŨåīį
    0.09
    (*)(
    0.09
     示
    0.08
    è¯Ĩ
    0.08
    æĹ·
    0.08
    è¡£
    0.08
    iment
    0.08
    Activations Density 0.016%

    No Known Activations