© 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. 23086
    Prev
    Next
    INDEX
    Explanations

    safely can begin finally proceed relax

    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¿ĺèĥ½
    -0.13
    -divider
    -0.09
    éľı
    -0.09
    æĢİä¹Īä¼ļ
    -0.09
    èĥ½åľ¨
    -0.08
    æİĢèµ·
    -0.08
    æķĻä½ł
    -0.08
    æĢİä¹Īåı¯èĥ½
    -0.08
    -Length
    -0.08
    æĢİä¹Īèĥ½
    -0.08
    POSITIVE LOGITS
    大èĥĨ
    0.12
    ä¸įå¿ħ
    0.12
    æĶ¾å¿ĥ
    0.11
    äºĨåIJ§
    0.10
     proceed
    0.10
     Proceed
    0.10
     safely
    0.09
    ç¨įç¨į
    0.09
     proceeds
    0.09
    å¼Ģå§ĭ
    0.09
    Activations Density 0.067%

    No Known Activations