© 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. 36332
    Prev
    Next
    INDEX
    Explanations

    a set of abstract classifications

    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
    ä¸Ģæŀļ
    -0.09
     alike
    -0.09
    1
    -0.08
    ä¸Ģæľ¬ä¹¦
    -0.08
    ary
    -0.08
    æ¾¹
    -0.08
    ä¸ĢçĤ¹
    -0.08
    owell
    -0.08
    9
    -0.08
    nh
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.15
    hev
    0.10
    earer
    0.10
    ç¥ĸ
    0.10
    é»ĺ认
    0.10
    quence
    0.09
    åĽºå®ļçļĦ
    0.09
    æªĢ
    0.09
    ascar
    0.09
    çĸijéĹ®
    0.09
    Activations Density 0.028%

    No Known Activations