© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9300
    Prev
    Next
    INDEX
    Explanations

    production of

    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
    åį¯
    -0.09
    ammer
    -0.09
    ä¸Ńæĸ¹
    -0.09
    纵横
    -0.08
    arters
    -0.08
    æ·»
    -0.08
    èĽĻ
    -0.08
    æī¿åĮħ
    -0.08
    èĭ¦
    -0.08
    å¦Ĭ
    -0.08
    POSITIVE LOGITS
    åIJİæľŁ
    0.11
    æľī幸
    0.10
    ëĭ´
    0.10
    éĤ£ç§į
    0.10
    饮æĸĻ
    0.10
    éĥ½è§īå¾Ĺ
    0.09
    è¿Ļç±»
    0.09
    ivec
    0.09
     dipped
    0.09
    /games
    0.09
    Activations Density 0.105%

    No Known Activations