© 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. 39733
    Prev
    Next
    INDEX
    Explanations

    reflect, light-colored, fuel economy

    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
    é±¼
    -0.09
    æ°´è´¨
    -0.08
    pite
    -0.08
    é£İæĻ¯åĮº
    -0.08
    aces
    -0.08
    @email
    -0.08
    çĸ¾
    -0.08
    çĪª
    -0.08
    赶快
    -0.08
     ode
    -0.07
    POSITIVE LOGITS
    éĤ£æ¬¡
    0.10
    çĻ½èī²çļĦ
    0.10
    /Gate
    0.10
    裸
    0.09
    æĽ
    0.09
    æī¿
    0.09
    orro
    0.09
    éļĶçĥŃ
    0.09
    .WHITE
    0.09
    ë©Ģ
    0.09
    Activations Density 0.036%

    No Known Activations