© 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. 8899
    Prev
    Next
    INDEX
    Explanations

    designed for

    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
    geois
    -0.09
    aci
    -0.09
    åѦä½į
    -0.09
    aran
    -0.09
    chest
    -0.09
     dong
    -0.09
    æĽ·
    -0.08
    cona
    -0.08
    ạnh
    -0.08
    UCT
    -0.08
    POSITIVE LOGITS
    è¿Ļç§įæĥħåĨµ
    0.12
    даÑĢ
    0.10
    åıijå¸ĥåħ¬åijĬ
    0.09
    æŀģé«ĺ
    0.09
    èĢĮæĪIJ
    0.09
    èĪį
    0.09
    èĢĮä¸Ķè¿ĺ
    0.08
    ä¸ŃéĢĶ
    0.08
    geries
    0.08
    å¸Ŀçİĭ
    0.08
    Activations Density 0.053%

    No Known Activations