© 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. 35630
    Prev
    Next
    INDEX
    Explanations

    type or form

    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
    oric
    -0.09
     alternatives
    -0.09
    alia
    -0.08
    _undo
    -0.08
     Butter
    -0.08
     tầm
    -0.08
    ´Ģ
    -0.08
     Darling
    -0.08
    kish
    -0.08
    Altern
    -0.08
    POSITIVE LOGITS
    æľīæīĢä¸įåIJĮ
    0.12
    åī¡
    0.11
    庶
    0.10
    ansa
    0.09
    ä¸įå°½
    0.09
    åĽłåľ°
    0.09
    æ¡Ģ
    0.09
    åįĥ亿
    0.09
    ä¸İåıijå±ķ
    0.09
    ä½ĵåŀĭ
    0.09
    Activations Density 0.706%

    No Known Activations