© 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. 18578
    Prev
    Next
    INDEX
    Explanations

    attacks on locations

    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
    ä¸ĢèĤ¡
    -0.10
    è¿·
    -0.09
    对æİ¥
    -0.09
    æ¿ĢåĬ¨
    -0.09
    æľ¬ç½ij
    -0.08
    èįĴ
    -0.08
    迷人
    -0.08
    èħķ
    -0.08
    ighth
    -0.08
    éļIJèĶ½
    -0.08
    POSITIVE LOGITS
    å¼±çĤ¹
    0.12
    èĦĨå¼±
    0.10
    èĸĦå¼±
    0.09
     vulnerability
    0.09
    éĺ²æĬ¤
    0.09
    è´¢çī©
    0.09
    éĺ²èĮĥ
    0.09
     unarmed
    0.09
    :key
    0.09
     tamil
    0.09
    Activations Density 0.095%

    No Known Activations