© 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. 5514
    Prev
    Next
    INDEX
    Explanations

    spreading information widely

    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
    æĿ¥çĶµ
    -0.09
    åħįè´£
    -0.09
    ç«Ļéķ¿
    -0.09
    odos
    -0.08
     caller
    -0.08
    åĪĽå§ĭ
    -0.08
     callers
    -0.08
    çŃ¹å»º
    -0.08
    bras
    -0.08
    仪表
    -0.08
    POSITIVE LOGITS
    ä¼łæĴŃ
    0.19
    è®©æĽ´å¤ļ
    0.16
    æī©æķ£
    0.16
     ÑĢаÑģпÑĢоÑģÑĤÑĢан
    0.15
    å¹¿æ³Ľ
    0.13
     widespread
    0.13
    æĽĿåħī
    0.13
     spread
    0.13
    åıĹä¼Ĺ
    0.12
    ç½ijç»ľä¼łæĴŃ
    0.12
    Activations Density 0.084%

    No Known Activations