© 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. 7543
    Prev
    Next
    INDEX
    Explanations

    be followed by a verb or noun

    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
    èĥ½æĬĬ
    -0.10
    èĥ½å¤Łåľ¨
    -0.10
    æľīèĥ½åĬĽ
    -0.10
    èĥ½å¤Ł
    -0.09
    èĥ½åľ¨
    -0.09
    便äºİ
    -0.09
    æĢİä¹Īä¼ļ
    -0.09
    tec
    -0.09
    èĥ½è¾¾åĪ°
    -0.09
    ä¹Łä¸įåı¯èĥ½
    -0.09
    POSITIVE LOGITS
    说æĺ¯
    0.12
    't
    0.12
    -être
    0.12
    çľĭåĩº
    0.11
    ’t
    0.11
    berra
    0.11
    è¿Ļä¹Ī说
    0.11
    å¾Īå¥½åľ°
    0.10
    ç®Ĺæĺ¯
    0.10
     даже
    0.10
    Activations Density 0.086%

    No Known Activations