© 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. 2005
    Prev
    Next
    INDEX
    Explanations

    try 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
    itel
    -0.11
    å¤§åľ°
    -0.10
    è´¨éĩıåĴĮ
    -0.09
    çĥľ
    -0.09
    åħģ
    -0.09
    bron
    -0.08
    æīĵçł´äºĨ
    -0.08
    æ³Ħ
    -0.08
    èĦ¸ä¸Ĭ
    -0.08
    åĬ¿å¿ħ
    -0.08
    POSITIVE LOGITS
    ä¸Ģä¸ĭ
    0.14
    äºĨä¸Ģä¸ĭ
    0.11
    äºĨ解ä¸Ģä¸ĭ
    0.10
    Ranges
    0.10
    åĭ¾
    0.10
    èĽī
    0.09
    äºĨå¾Īå¤ļ
    0.09
    æĬĬ她
    0.09
    éĿŀ常å¤ļ
    0.09
    妹
    0.09
    Activations Density 0.111%

    No Known Activations