© 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. 27072
    Prev
    Next
    INDEX
    Explanations

    security and privacy

    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
    çĺł
    -0.09
    åĬ©
    -0.09
     exc
    -0.09
    èĬĤæ°´
    -0.08
    éģĴ
    -0.08
    (exc
    -0.08
    achinery
    -0.08
    edian
    -0.08
    帮æī¶
    -0.08
    ÑĢеÑģ
    -0.08
    POSITIVE LOGITS
     security
    0.16
    éĺ²èĮĥ
    0.15
    éĺ²æĬ¤
    0.14
    åł¡åŀĴ
    0.14
    ä¿ĿæĬ¤
    0.14
    Security
    0.14
    çļĦå®īåħ¨
    0.13
     Security
    0.13
    security
    0.13
    -security
    0.13
    Activations Density 0.232%

    No Known Activations