© 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. 54167
    Prev
    Next
    INDEX
    Explanations

    challenge description

    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
    带åĽŀ
    -0.09
    ria
    -0.09
    æĻ¯
    -0.09
    ERIC
    -0.09
     mặc
    -0.08
    æİł
    -0.08
    æݨ
    -0.08
    éĢı
    -0.08
    cion
    -0.08
    âĩ¨
    -0.08
    POSITIVE LOGITS
    åħ¨èĥ½
    0.10
    å¥ĸéĩij
    0.10
    对å¤ĸå¼ĢæĶ¾
    0.09
    å®ŀè´¨
    0.09
    æĶ»åħĭ
    0.09
    æĮijæĪĺ
    0.09
    è±ķ
    0.09
    åIJł
    0.09
    ç»Ĵ
    0.09
    ounty
    0.09
    Activations Density 0.204%

    No Known Activations