© 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. 20049
    Prev
    Next
    INDEX
    Explanations

    control bleeding

    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
    odi
    -0.10
    å®ŀæĸ½ç»ĨåĪĻ
    -0.10
    ä¸ĢæŃ¥
    -0.09
    logan
    -0.09
    æ£ł
    -0.09
    odal
    -0.09
    轺
    -0.09
    Ñģк
    -0.09
    çĸĻ
    -0.09
    .instructions
    -0.09
    POSITIVE LOGITS
    ago
    0.09
    以ä¸ĭåĩłä¸ª
    0.09
    åĴĮå®ĮåĸĦ
    0.08
    ibrator
    0.08
    /manage
    0.08
    _bp
    0.08
    /control
    0.08
    çľº
    0.08
    宽度
    0.08
     emotions
    0.07
    Activations Density 0.052%

    No Known Activations