© 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. 50537
    Prev
    Next
    INDEX
    Explanations

    felt compelled to follow

    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
    æ½®æµģ
    -0.10
    edor
    -0.09
    å°±è·Ł
    -0.09
    former
    -0.08
     Hag
    -0.08
    åĽºçĦ¶
    -0.08
    ãģı
    -0.08
    veral
    -0.08
    çĤ³
    -0.08
     Own
    -0.08
    POSITIVE LOGITS
    羣æŃ£
    0.17
     überhaupt
    0.14
    羣æŃ£çļĦ
    0.14
     ÑģобÑģÑĤвенно
    0.13
    åĭī强
    0.12
     truly
    0.12
    çķ¥å¾®
    0.12
     realmente
    0.12
    ç¨įå¾®
    0.11
    çķ¥
    0.11
    Activations Density 0.206%

    No Known Activations