© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52570
    Prev
    Next
    INDEX
    Explanations

    more or better

    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
    è¶ħè¿ĩäºĨ
    -0.11
    ie
    -0.09
    éģ
    -0.09
    iram
    -0.09
    stud
    -0.09
    iry
    -0.09
     dit
    -0.09
    è¶ħè¿ĩ
    -0.08
    dit
    -0.08
    è¶³å¤Ł
    -0.08
    POSITIVE LOGITS
    æĽ´æľī
    0.10
    çľĭçĤ¹
    0.10
    æĽ´åħ·
    0.09
    ãģ»ãģĨãģĮ
    0.09
    æĽ´å®¹æĺĵ
    0.09
    åĿIJçĿĢ
    0.09
    çŀ©çĽ®
    0.09
    å¯ĴåĨ¬
    0.08
    å®ŀè´¨æĢ§
    0.08
    çļĦä¸ĢéĿ¢
    0.08
    Activations Density 0.165%

    No Known Activations