© 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. 62887
    Prev
    Next
    INDEX
    Explanations

    before the court

    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
    è©
    -0.10
    ì½ľ
    -0.09
    ä¸īæĸ¹
    -0.09
     horn
    -0.09
    èĦ±ç¦»
    -0.09
    æľ¬èº«çļĦ
    -0.08
    纡
    -0.08
    èĩªèº«çļĦ
    -0.08
    æĹ¶ä»£
    -0.08
     Dip
    -0.08
    POSITIVE LOGITS
    éĿ¢åīį
    0.10
    äº®çĽ¸
    0.10
    éľ²
    0.09
    æķŀ
    0.09
    çľ¼åīį
    0.09
    è¹Ĵ
    0.09
    OG
    0.09
    çľ¼åīįçļĦ
    0.08
    æįĤ
    0.08
    ekt
    0.08
    Activations Density 0.076%

    No Known Activations