© 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. 35128
    Prev
    Next
    INDEX
    Explanations

    enlargement and increase

    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
    ç¿Ĭ
    -0.09
    å¿ĥè¡Ģ
    -0.09
    èł²
    -0.09
    çļĦéĤ£ä¸Ģ
    -0.09
    åIJİå¤ĩ
    -0.08
    让èĩªå·±
    -0.08
    åľ¨äº¬
    -0.08
    举åĬŀçļĦ
    -0.08
    MA
    -0.08
    éħĿéħ¿
    -0.08
    POSITIVE LOGITS
    ç´Ĭä¹±
    0.11
    è¿ĩå¤ļ
    0.10
    itti
    0.10
    å¼Ĥ常
    0.09
    è¿ŀè¿ŀ
    0.09
    ç®ĢåĮĸ
    0.09
    å¢ŀå¤ļ
    0.08
     disorder
    0.08
    ç»Ī
    0.08
    缺å°ij
    0.08
    Activations Density 0.570%

    No Known Activations