© 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. 2263
    Prev
    Next
    INDEX
    Explanations

    summary of

    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
    å°ıåŃ©åŃIJ
    -0.11
    udad
    -0.10
    滢
    -0.09
    请éĹ®
    -0.09
    éļ¶å±ŀäºİ
    -0.09
    康
    -0.09
    åī²
    -0.09
    vero
    -0.09
    被迫
    -0.09
    ocol
    -0.09
    POSITIVE LOGITS
    æ¦Ĥæĭ¬
    0.12
    è¦ģçĤ¹
    0.10
    å½Ĵ纳
    0.10
    åīįä¸ĸ
    0.09
    大æ¦Ĥ
    0.09
    主è¦ģåĨħ容
    0.09
     major
    0.09
    éĢŁ
    0.09
    大èĩ´
    0.09
    çªģåĩº
    0.08
    Activations Density 0.226%

    No Known Activations