© 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. 4746
    Prev
    Next
    INDEX
    Explanations

    doesn't work

    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
    èĩ¾
    -0.10
    æı´
    -0.10
    æīĢæıIJä¾Ľ
    -0.09
    ä¾ĥ
    -0.09
    .DOM
    -0.09
    æħij
    -0.08
    åľ¨ä»ĸçļĦ
    -0.08
     WaitFor
    -0.08
    ption
    -0.08
    çļĦåĬĽéĩı
    -0.08
    POSITIVE LOGITS
    åĩºçİ°äºĨ
    0.09
    æĤ²åī§
    0.09
     STILL
    0.09
    ä»įçĦ¶
    0.09
    ä¾ĿçĦ¶
    0.09
    解åĨ³éĹ®é¢ĺ
    0.09
    产çĶŁäºĨ
    0.09
    åĩºçİ°
    0.09
    ulla
    0.08
    ä»į
    0.08
    Activations Density 0.184%

    No Known Activations