© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35741
    Prev
    Next
    INDEX
    Explanations

    believe me / promise me

    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»įæľª
    -0.10
    çĤ¹äºĨ
    -0.09
    èĢģå¹´
    -0.09
    ì²Ń
    -0.09
     Probe
    -0.09
    æķ´é½IJ
    -0.09
    æĮĩçĤ¹
    -0.09
    æľ¬çĿĢ
    -0.08
    çļĦæĸ°
    -0.08
    äºĭåĦ¿
    -0.08
    POSITIVE LOGITS
    gere
    0.09
    ãģĵãĤĮãģ¯
    0.09
    åľ°è¯´
    0.09
    åĬŀæ¡Ī
    0.08
    åĬĿ
    0.08
    è¿Ļæĺ¯ä¸Ģ个
    0.08
    æ²®
    0.08
    è¿Ļä¸įæĺ¯
    0.08
    rey
    0.08
    è¿Ļæĺ¯ä¸Ģç§į
    0.08
    Activations Density 0.005%

    No Known Activations