© 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. 53540
    Prev
    Next
    INDEX
    Explanations

    confidence and comfort

    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
    çĬĢ
    -0.09
    ä¸Ģéĥ¨
    -0.09
    æĹ¶å¸¸
    -0.09
    åĪ©çĽĬ
    -0.09
    OTS
    -0.08
    çļĦ巨大
    -0.08
    åħ¬è®¤
    -0.08
    ä¸Ģçīĩ
    -0.08
    çºłçº·
    -0.08
    çŃīåĢĻ
    -0.08
    POSITIVE LOGITS
    åºķæ°Ķ
    0.20
    ä¿¡å¿ĥ
    0.19
    èĩªä¿¡
    0.19
     confidence
    0.17
    çļĦä¿¡å¿ĥ
    0.17
     Confidence
    0.16
    æľīä¿¡å¿ĥ
    0.16
     confident
    0.16
     ÑĥвеÑĢен
    0.16
    confidence
    0.16
    Activations Density 0.051%

    No Known Activations