© 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. 53476
    Prev
    Next
    INDEX
    Explanations

    in the absence of

    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
    庵
    -0.10
    æŁĶæĢ§
    -0.10
    éłĵ
    -0.09
    é¥Ń
    -0.09
    æĪ¡
    -0.09
    深深
    -0.09
    èĩªè´Ł
    -0.09
    ØŃس
    -0.09
     Flake
    -0.09
    /inc
    -0.08
    POSITIVE LOGITS
     absence
    0.15
    缺ä¹ı
    0.14
    没æľī
    0.12
    å¦Ĥæŀľæ²¡æľī
    0.11
     absent
    0.11
     without
    0.11
    Absent
    0.11
    æĺ¯æ²¡æľī
    0.11
    without
    0.11
    Without
    0.10
    Activations Density 0.097%

    No Known Activations