© 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. 7415
    Prev
    Next
    INDEX
    Explanations

    up the ladder

    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
    认
    -0.09
    彩
    -0.08
     hopefully
    -0.08
    áµĴ
    -0.08
    æ¶ī
    -0.08
    è¿·
    -0.08
    ä¸Ģç»ı
    -0.08
    _texts
    -0.08
    ä¸ĢæŦ
    -0.08
     diss
    -0.08
    POSITIVE LOGITS
    家éŨåı£
    0.13
    èĢĮä¸įæĺ¯
    0.12
    arus
    0.11
     chứ
    0.10
    主åĬ¨
    0.10
    èĢĮéĿŀ
    0.10
    rather
    0.10
    主åĭķ
    0.10
    å°±è¿ij
    0.10
    ä¸ĬéŨ
    0.10
    Activations Density 0.033%

    No Known Activations