© 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. 37041
    Prev
    Next
    INDEX
    Explanations

    Shawn, Dawn, Darren, dopamine

    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
    RARY
    -0.10
    -minded
    -0.10
     minded
    -0.10
    idor
    -0.09
    oj
    -0.09
    erate
    -0.09
    ÂŃs
    -0.09
    UCH
    -0.09
    Ñģп
    -0.09
    oster
    -0.09
    POSITIVE LOGITS
    /or
    0.14
    /OR
    0.11
    fulness
    0.11
    ãģ»ãģĨ
    0.11
    sWith
    0.10
    rox
    0.09
    side
    0.09
    ses
    0.09
    åµĺ
    0.09
    manship
    0.09
    Activations Density 0.013%

    No Known Activations