© 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. 18170
    Prev
    Next
    INDEX
    Explanations

    veteran

    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
    涤
    -0.09
    /classes
    -0.09
    ãģªãĤĬ
    -0.08
    ãģ£ãģįãĤĬ
    -0.08
    ä¸Ģ个个
    -0.08
    æľªæĿ¥åıijå±ķ
    -0.08
    åĢĮ
    -0.07
    æݾ
    -0.07
    loading
    -0.07
    ä»ĸ人
    -0.07
    POSITIVE LOGITS
     пÑĢож
    0.10
    аÑİÑĤÑģÑı
    0.09
    geber
    0.09
    ubs
    0.09
    ä¸įå°ıçļĦ
    0.09
    è¶ĭåĬ¿
    0.09
    eros
    0.09
    ivals
    0.09
    Subview
    0.09
    ship
    0.09
    Activations Density 0.003%

    No Known Activations