© 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. 11240
    Prev
    Next
    INDEX
    Explanations

    rule and ruler

    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
    çªĿ
    -0.11
    æ¢ħèĬ±
    -0.10
    éºĭ
    -0.10
    èĽĢ
    -0.10
    ä¹IJæĦı
    -0.10
    æī¾å·¥ä½ľ
    -0.10
    PropertyParams
    -0.10
    ROTO
    -0.09
    tle
    -0.09
    ä¼ĹæīĢ
    -0.09
    POSITIVE LOGITS
    eer
    0.10
    adores
    0.09
    elp
    0.08
    èĢħçļĦ
    0.08
    hip
    0.08
    fully
    0.08
    ember
    0.08
    iser
    0.08
     Tin
    0.08
    aires
    0.07
    Activations Density 0.016%

    No Known Activations