© 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. 26658
    Prev
    Next
    INDEX
    Explanations

    many people fail or suffer

    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
    _CURSOR
    -0.09
    à¸ļรร
    -0.09
    å°¼æĸ¯
    -0.09
    åĬ¨åijĺ
    -0.09
    ç§Łè½¦
    -0.09
    ENDIF
    -0.09
    çĤĬ
    -0.09
    .CreateInstance
    -0.09
    çªģçĦ¶
    -0.09
    STA
    -0.09
    POSITIVE LOGITS
    éĶĻ误
    0.10
    å¥ī
    0.10
    å¤ļæķ°
    0.09
    误åĮº
    0.09
    大å¤ļæķ°äºº
    0.09
    çĽ²çĽ®
    0.09
    æ´»
    0.08
    å¾Ģå¾Ģæĺ¯
    0.08
    大éĥ¨åĪĨ
    0.08
    忽è§Ĩ
    0.08
    Activations Density 0.164%

    No Known Activations