© 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. 2069
    Prev
    Next
    INDEX
    Explanations

    surrounding areas

    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¸İåħ¶ä»ĸ
    -0.12
    çľ¼åīįçļĦ
    -0.11
    çľ¼åīį
    -0.11
    åħ¶ä¸Ńä¸Ģ个
    -0.10
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.10
    éĹ¨æ§Ľ
    -0.10
    enal
    -0.10
    ä¸ĢåĪĻ
    -0.09
    åı¦å¤ĸä¸Ģ个
    -0.09
    åŃĺåľ¨äºİ
    -0.09
    POSITIVE LOGITS
    åij¨è¾¹
    0.11
     surrounding
    0.11
    ä¸įè¿ľå¤Ħ
    0.10
    åľ°åĮºçļĦ
    0.09
    unos
    0.09
    åįıåIJĮåıijå±ķ
    0.09
    ä¹ĥèĩ³
    0.09
    å¾ĭ
    0.09
    åľ°åĮº
    0.08
    åľ°åįĢ
    0.08
    Activations Density 0.042%

    No Known Activations