© 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. 53465
    Prev
    Next
    INDEX
    Explanations

    end of sentence

    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
    çľĭæ¸ħ
    -0.09
    马ä¸Ĭ
    -0.09
    uen
    -0.09
    sky
    -0.08
    çļĸ
    -0.08
    shed
    -0.08
    ivery
    -0.08
    suit
    -0.08
    Suit
    -0.08
     hog
    -0.08
    POSITIVE LOGITS
    åģı
    0.14
    åģıåIJij
    0.13
    ä¿Ŀå®Ī
    0.10
    å¾Ģ
    0.10
    èµ°ä¸Ĭ
    0.10
    åĢ¾åIJijäºİ
    0.10
    ä¸įçķĻ
    0.09
    éĢĬ
    0.09
    IRS
    0.09
    åģıä½İ
    0.08
    Activations Density 0.053%

    No Known Activations