© 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. 47972
    Prev
    Next
    INDEX
    Explanations

    and other

    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
    å®Įæķ´
    -0.09
    çĭ¸
    -0.08
    è¿Ļäºĭ
    -0.08
    ÑĭÑĪ
    -0.08
    éĤ£ä¸ĢåĪ»
    -0.08
    å¥ģ
    -0.08
    pdf
    -0.08
    临
    -0.08
    rier
    -0.08
    borg
    -0.08
    POSITIVE LOGITS
    ëĵ¤ëıĦ
    0.10
    umba
    0.10
    å¾ħéģĩ
    0.10
    åĽ½ç±į
    0.09
    ä¸Ģè´¯
    0.09
    çĶŁæ´»æ°´å¹³
    0.09
    åľ°ä½į
    0.09
    ãĥ¼ãĥł
    0.09
    诸å¦Ĥ
    0.09
    å¾ĹåĪĨ
    0.09
    Activations Density 0.103%

    No Known Activations