© 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. 20160
    Prev
    Next
    INDEX
    Explanations

    next time you

    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¸Ģè¾ĪåŃIJ
    -0.12
    延伸
    -0.09
    æĸ°æĹ¶ä»£
    -0.09
     RSS
    -0.08
    alker
    -0.08
     бÑĥкв
    -0.08
    RSS
    -0.08
    æĶ¹è®Ĭ
    -0.08
    ä¸įåIJĮçļĦ
    -0.08
    _CLR
    -0.08
    POSITIVE LOGITS
    è§ģåĪ°
    0.11
    éģĩåĪ°
    0.10
    è§īå¾Ĺ
    0.10
    tempt
    0.09
    æĥ³åĪ°
    0.09
    æ£ĺ
    0.09
    ä¸ĭ次
    0.09
    ä¹ı
    0.09
    æĥ³èµ·
    0.08
    éľĢè¦ģçĶ¨åĪ°
    0.08
    Activations Density 0.013%

    No Known Activations