© 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. 11078
    Prev
    Next
    INDEX
    Explanations

    past events and actions

    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
    å±ĬæŶ
    -0.14
    è¿ijå¹´æĿ¥
    -0.12
    åĪ°æŶåĢĻ
    -0.11
    å½ĵæŶ
    -0.11
    å¤ļå¹´æĿ¥
    -0.10
    缮åīįå·²
    -0.10
    è¿ijäºĽå¹´
    -0.10
    缮åīį
    -0.10
    å¹³æŶ
    -0.10
    æĪijå½ĵæŶ
    -0.10
    POSITIVE LOGITS
    kek
    0.10
    è¿ĺä¸į
    0.10
    æ±Łä¸ľ
    0.09
    åıªä¼ļ
    0.09
    åı¯æĺ¯
    0.09
    ä¹Łæĺ¯å¦ĤæѤ
    0.09
    éĥ½ä¼ļæľī
    0.08
    ìĶ©
    0.08
    ogra
    0.08
    anson
    0.08
    Activations Density 0.052%

    No Known Activations