© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9202
    Prev
    Next
    INDEX
    Explanations

    Brian followed by last name

    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
    Ŀ
    -0.10
    éĩįè¦ģæĦıä¹ī
    -0.10
    累累
    -0.09
    еÑĢÑĮ
    -0.09
    erah
    -0.09
    onica
    -0.09
    LECTION
    -0.09
    å¯IJ
    -0.08
    iler
    -0.08
    毽
    -0.08
    POSITIVE LOGITS
    fully
    0.10
    semb
    0.10
    liest
    0.10
    alysis
    0.10
    ships
    0.10
    otas
    0.10
    ness
    0.10
    ne
    0.09
     помоÑī
    0.09
    atics
    0.09
    Activations Density 0.017%

    No Known Activations