© 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. 39547
    Prev
    Next
    INDEX
    Explanations

    advantage and control

    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
    åĨħå¹ķ
    -0.09
     kab
    -0.09
     unt
    -0.08
    æľīæĿ¡ä»¶çļĦ
    -0.08
    åķĨçĶ¨
    -0.08
    纵
    -0.08
     Moder
    -0.08
    çªį
    -0.08
     Stub
    -0.08
     airst
    -0.08
    POSITIVE LOGITS
    åİĭåĪ¶
    0.10
    é¾Ł
    0.10
    è²Ķ
    0.10
    SENT
    0.09
    buzz
    0.09
    çĽ¸å¯¹æĿ¥è¯´
    0.09
    åįłåľ°
    0.09
     Walnut
    0.08
    mour
    0.08
    æ®Ĭ
    0.08
    Activations Density 0.029%

    No Known Activations