© 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. 56351
    Prev
    Next
    INDEX
    Explanations

    edge or rim

    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
    è´«ç©·
    -0.10
    åģľæ»ŀ
    -0.09
    ë¹ħ
    -0.09
    ctic
    -0.08
     cages
    -0.08
    åİ»æİī
    -0.08
    yal
    -0.08
    enti
    -0.08
    бав
    -0.08
    åľ°ä¸ĭæ°´
    -0.08
    POSITIVE LOGITS
    ä¸ĢåľĪ
    0.12
    ä¸Ģåij¨
    0.11
    åľĪ
    0.10
    éĤĬ
    0.10
    è¾¹
    0.10
    Edge
    0.09
    å¤Ħ
    0.09
     edge
    0.09
    å¾ĹäºĨ
    0.09
    _edge
    0.09
    Activations Density 0.099%

    No Known Activations