© 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. 30528
    Prev
    Next
    INDEX
    Explanations

    threaten, defend, prevent, preserve, safeguard

    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
    åħ¨æĿij
    -0.10
    åĩ¿
    -0.09
    éªĮ
    -0.09
    éĢł
    -0.08
    éģ¥è¿ľ
    -0.08
    æ¸Ķæ°ij
    -0.08
    ç©·
    -0.08
    å·®å¼ĤåĮĸ
    -0.08
    ä¿¡æģ¯åıijå¸ĥ
    -0.08
    åŃļ
    -0.08
    POSITIVE LOGITS
    ä¿Ŀåį«
    0.12
     threatened
    0.10
    ä¸įåıĹ
    0.10
    éĿ¢ä¸´
    0.10
     preserving
    0.10
    ä¿ĿæĬ¤
    0.10
     safeguard
    0.10
     ÑģоÑħÑĢан
    0.10
     preservation
    0.10
    ä¿Ŀä½ı
    0.10
    Activations Density 0.098%

    No Known Activations