© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50734
    Prev
    Next
    INDEX
    Explanations

    shape description

    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
    åįĵ
    -0.11
    oking
    -0.09
    gres
    -0.09
    士
    -0.09
    ISTER
    -0.09
    ë¥ł
    -0.09
    bies
    -0.09
    smith
    -0.09
    ä¸Ŀ
    -0.09
    ockey
    -0.08
    POSITIVE LOGITS
    -corner
    0.10
    åĴĮå®ĮåĸĦ
    0.10
    0.09
    å®ĮåĸĦ
    0.09
    éĢļçĶ¨
    0.09
    -round
    0.08
    pty
    0.08
     Rounded
    0.08
    rounded
    0.08
     Stones
    0.08
    Activations Density 0.021%

    No Known Activations