© 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. 50337
    Prev
    Next
    INDEX
    Explanations

    open or exposed states

    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
    akis
    -0.10
    带ä¸Ĭ
    -0.10
    絡
    -0.10
    éĩįä¸Ń
    -0.10
    .rd
    -0.09
    ritis
    -0.09
    ä¸į让
    -0.09
    èģĨ
    -0.09
    éī´
    -0.09
    çİĭåŃIJ
    -0.09
    POSITIVE LOGITS
    æķŀ
    0.19
    æļ´éľ²
    0.18
    å¼ĢæĶ¾
    0.16
    æķŀå¼Ģ
    0.16
     open
    0.15
     exposed
    0.14
    éĸĭæĶ¾
    0.12
    open
    0.12
    Exposed
    0.12
     exposures
    0.11
    Activations Density 0.107%

    No Known Activations