© 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. 48756
    Prev
    Next
    INDEX
    Explanations

    pillar and column structures

    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
    olley
    -0.11
    emia
    -0.10
    lay
    -0.10
    èĬľ
    -0.09
    åijĺ
    -0.09
    ë£Į
    -0.09
    è¿Ŀ
    -0.09
    æıĨ
    -0.08
    ru
    -0.08
    _hpp
    -0.08
    POSITIVE LOGITS
     pillar
    0.10
    pillar
    0.10
     pillars
    0.10
    æĶ¯æŁ±
    0.09
     Pill
    0.09
    -mounted
    0.09
    åĴ±ä»¬
    0.09
    åĽĽä¸ªæĦıè¯Ĩ
    0.09
    ç¡Ģ
    0.09
    对èĩªå·±
    0.09
    Activations Density 0.014%

    No Known Activations