© 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. 17538
    Prev
    Next
    INDEX
    Explanations

    Equal Opportunity Employer

    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
    ä¾ĽåºĶéĵ¾
    -0.10
    度è¿ĩ
    -0.09
    åĨį说
    -0.09
    临
    -0.08
    éĻįä½İæĪIJæľ¬
    -0.08
     Abr
    -0.08
    èĥ¶åĽĬ
    -0.08
    好ä¸į容æĺĵ
    -0.08
    æŃ£éĿ¢
    -0.08
     geli
    -0.08
    POSITIVE LOGITS
    astle
    0.10
    追赶
    0.09
    æĸĹ
    0.09
     lÃłnh
    0.08
    nej
    0.08
    追
    0.08
    éĩįçĤ¹
    0.08
    akan
    0.08
    uala
    0.08
    è¢Ĥ
    0.08
    Activations Density 0.011%

    No Known Activations