© 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. 35181
    Prev
    Next
    INDEX
    Explanations

    ear and related anatomy

    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
    CLE
    -0.11
     cle
    -0.11
    ä¸Ģ件
    -0.09
    æIJŃ
    -0.09
    alem
    -0.09
    erable
    -0.09
    çļĦçĶ·äºº
    -0.09
    _PS
    -0.08
    å¹³åİŁ
    -0.08
    åĸĥ
    -0.08
    POSITIVE LOGITS
     fly
    0.10
     Fly
    0.09
     Posting
    0.09
    Fly
    0.09
    é£ŀ
    0.09
    çĭİ
    0.09
    ldr
    0.08
    æŃ»åİ»
    0.08
    è¯ł
    0.08
    -fly
    0.08
    Activations Density 0.222%

    No Known Activations