© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51487
    Prev
    Next
    INDEX
    Explanations

    forum discussions and posts

    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
    Ñģоб
    -0.09
    arella
    -0.09
    TP
    -0.09
    .dw
    -0.08
    umm
    -0.08
    åĨ³ä¸į
    -0.08
    ä¸įåĪĨ
    -0.08
    aminer
    -0.08
    attended
    -0.08
    _DIRS
    -0.08
    POSITIVE LOGITS
    åĿĽ
    0.11
    .arg
    0.10
    imers
    0.09
    åĿ
    0.09
    论åĿĽ
    0.09
    åīįéĢĶ
    0.09
     SCN
    0.09
    ä¸įåİ»
    0.09
    ç«ł
    0.09
    æĸ¯åŁº
    0.09
    Activations Density 0.124%

    No Known Activations