© 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. 36396
    Prev
    Next
    INDEX
    Explanations

    time ranges

    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
    åģ·
    -0.10
    å°Ĩè¿Ľä¸ĢæŃ¥
    -0.10
    ä½ľå¼Ĭ
    -0.10
    代è¨Ģ
    -0.09
    符åı·
    -0.09
    åįĥåı¤
    -0.09
    æ¬
    -0.09
    åį«è§Ĩ
    -0.09
    å¯ĵæĦı
    -0.09
    èįĩ
    -0.09
    POSITIVE LOGITS
    åħ³éŨ
    0.10
    æĹ©æĹ©
    0.08
    é»İæĺİ
    0.08
    HexString
    0.08
    çķĻå®Ī
    0.08
     Shutdown
    0.08
    Absent
    0.08
    labs
    0.08
    éĨĽ
    0.07
    ãģĦãģŁãģłãģijãĤĭ
    0.07
    Activations Density 0.024%

    No Known Activations