© 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. 2350
    Prev
    Next
    INDEX
    Explanations

    check-in times

    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
    æ¶ķ
    -0.09
    æĪij没
    -0.09
    inous
    -0.09
    vents
    -0.08
     Beard
    -0.08
    èĺ¸
    -0.08
    æĥłåıĬ
    -0.08
    家åĸ»
    -0.08
    viso
    -0.08
    atus
    -0.08
    POSITIVE LOGITS
    este
    0.10
     оÑĤз
    0.10
    çĶ¨æĪ·æıIJä¾Ľ
    0.09
    书éĻ¢
    0.09
    getRepository
    0.08
    моÑĢ
    0.08
    æĮģæľīçļĦ
    0.08
    ä»»ä½ķæŶåĢĻ
    0.08
    edException
    0.08
    atables
    0.08
    Activations Density 0.016%

    No Known Activations