© 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. 6712
    Prev
    Next
    INDEX
    Explanations

    numbers or measurements following preceding word

    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
    çīĪæĿĥå½Ĵ
    -0.10
    饺
    -0.10
    æł¹æľ¬å°±ä¸į
    -0.10
    个å°ı
    -0.09
    baugh
    -0.09
    iplinary
    -0.09
    为æĤ¨æıIJä¾Ľ
    -0.09
    ILE
    -0.09
    æ°¸ä¹ħ
    -0.09
    æ±Ģ
    -0.09
    POSITIVE LOGITS
    åįłæľī
    0.09
     adj
    0.08
     finished
    0.08
    æĽ³
    0.08
    اÙĪÙĬ
    0.07
     Banc
    0.07
    åĽĽäºĶ
    0.07
    梳
    0.07
    FieldValue
    0.07
     pred
    0.07
    Activations Density 0.198%

    No Known Activations