© 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. 19321
    Prev
    Next
    INDEX
    Explanations

    learn to

    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
    æŃ£åĢ¼
    -0.10
    å¾Ĺèµ·
    -0.08
    äºĶä¸Ģ
    -0.08
    çİ°åľ¨
    -0.08
     unnamed
    -0.08
    edBy
    -0.08
    注å®ļ
    -0.08
    unto
    -0.08
    åĶ®ç¥¨
    -0.07
    ä¸ĢåIJį
    -0.07
    POSITIVE LOGITS
    ä»ĸ们éĥ½
    0.09
    ä½İä¸ĭ
    0.09
    æݼ
    0.09
    ê³¼ìłķ
    0.08
    osas
    0.08
    ä¸ĢéŨ
    0.08
     Ñģами
    0.08
    หม
    0.08
    éŨåīį
    0.08
    wie
    0.08
    Activations Density 0.011%

    No Known Activations