© 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. 47888
    Prev
    Next
    INDEX
    Explanations

    integration, audio, video

    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
     "()
    -0.10
    ecycle
    -0.10
    ë¹Ľ
    -0.09
    KE
    -0.09
    ä¸İåħ¶ä»ĸ
    -0.09
    åıijçĶŁçļĦ
    -0.09
    è¡¡æ°´
    -0.09
    ICT
    -0.09
    .Mobile
    -0.09
     TECHNO
    -0.08
    POSITIVE LOGITS
    ä¾ı
    0.10
    åĮħ容
    0.09
    è¡·
    0.09
    èĩ£
    0.09
    éĶĻ
    0.09
    大桥
    0.09
    èıľåįķ
    0.08
    æĹ©æĻļ
    0.08
    ä½°
    0.08
    artin
    0.08
    Activations Density 0.097%

    No Known Activations