© 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. 63604
    Prev
    Next
    INDEX
    Explanations

    by administrative authorities

    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»ĸåľ¨
    -0.10
    terra
    -0.09
    å°ıåŃ©
    -0.09
    被è¯Ħ为
    -0.09
    è¿·æĥij
    -0.09
    elman
    -0.09
    anie
    -0.09
    æĺ¨
    -0.09
    çĶ·åŃ©åŃIJ
    -0.08
    被æī§è¡Į
    -0.08
    POSITIVE LOGITS
    çģ¼
    0.09
    æľīåħ³éĥ¨éŨ
    0.09
     authorities
    0.09
    æİĪ
    0.08
    ä¸Ģåı£
    0.08
    缸åħ³éĥ¨éŨ
    0.08
    æĬĬæīĭ
    0.08
    ãģĶ
    0.08
    å½ĵå±Ģ
    0.07
    Locator
    0.07
    Activations Density 0.089%

    No Known Activations