© 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. 37439
    Prev
    Next
    INDEX
    Explanations

    refer to the

    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
    okes
    -0.11
    .instagram
    -0.10
    .ERR
    -0.10
    CLUD
    -0.10
    à¸Ľà¸ı
    -0.10
    adoo
    -0.10
    acomment
    -0.10
    .EVT
    -0.09
    uly
    -0.09
    .truth
    -0.09
    POSITIVE LOGITS
     “
    0.10
    å®ļäºĨ
    0.09
    _WS
    0.09
    (
    0.08
    常说
    0.08
    è°ĵ
    0.08
    æ´¥
    0.08
    "
    0.08
     "
    0.07
    0.07
    Activations Density 0.094%

    No Known Activations