© 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. 1082
    Prev
    Next
    INDEX
    Explanations

    license and/or terms

    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
    çIJĨ解åĴĮ
    -0.27
    管çIJĨåĴĮ
    -0.25
    ç»ıéªĮåĴĮ
    -0.24
    ä¼ģä¸ļåĴĮ
    -0.21
    建设åĴĮ
    -0.21
    è´¨éĩıåĴĮ
    -0.21
    èĥ½åĬĽåĴĮ
    -0.20
    çĶŁäº§åĴĮ
    -0.19
    æĸĩåĮĸåĴĮ
    -0.19
    æŶéĹ´åĴĮ
    -0.19
    POSITIVE LOGITS
    /or
    0.64
    /OR
    0.32
    /of
    0.27
    /o
    0.26
    rogen
    0.25
    rew
    0.25
    rog
    0.25
    èĶ¼
    0.22
    åħ¶å®ĥ
    0.21
    Ñģком
    0.20
    Activations Density 1.770%

    No Known Activations