© 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. 54741
    Prev
    Next
    INDEX
    Explanations

    strategy and approach

    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¸Ĥåľºä¸»ä½ĵ
    -0.11
    缴è¨Ģ
    -0.09
    æ¶Įçİ°
    -0.08
    åģļä¸ĢäºĽ
    -0.08
    erty
    -0.08
    éĵŃ
    -0.08
    æĭ§
    -0.08
    lime
    -0.08
    åĪĹ举
    -0.07
    æĮ¤åİĭ
    -0.07
    POSITIVE LOGITS
    çŃĸçķ¥
    0.27
     plan
    0.26
     strategy
    0.26
    计åĪĴ
    0.25
    plan
    0.20
    æĸ¹æ¡Ī
    0.20
    å®ŀæĸ½æĸ¹æ¡Ī
    0.20
     план
    0.20
    è¨ĪåĬĥ
    0.20
     Strategy
    0.20
    Activations Density 0.151%

    No Known Activations