© 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. 5304
    Prev
    Next
    INDEX
    Explanations

    for some reason

    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
    认æ¸ħ
    -0.11
    OptionsResolver
    -0.09
    æŁı
    -0.09
    ÑĤек
    -0.09
    tems
    -0.09
    åħĪè¿Ľ
    -0.09
    gado
    -0.08
    å¾Īå¿«
    -0.08
    足
    -0.08
    arters
    -0.08
    POSITIVE LOGITS
    åİŁåĽł
    0.15
    ä»Ģä¹ĪåİŁåĽł
    0.15
     reason
    0.13
    çļĦåİŁåĽł
    0.13
     reasons
    0.13
    reason
    0.12
    主è¦ģåİŁåĽł
    0.12
    ä¸įåı¯æĢĿè®®
    0.11
    ä¸įæĺİ
    0.11
    çļĦç¼ĺæķħ
    0.11
    Activations Density 0.057%

    No Known Activations