© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5333
    Prev
    Next
    INDEX
    Explanations

    questions starting with why or how

    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
     xuyên
    -0.10
    å®ģ
    -0.09
    åĵ²
    -0.09
     лиÑĪÑĮ
    -0.08
     оÑĦоÑĢмлен
    -0.08
    责任åĪ¶
    -0.08
    plete
    -0.08
    ening
    -0.08
    èij«
    -0.08
     stocking
    -0.08
    POSITIVE LOGITS
    æĺ¯åľ¨
    0.10
    ters
    0.09
    onn
    0.09
    æĭĪ
    0.08
    æİĴ
    0.08
    çİ°æľī
    0.08
    ton
    0.08
    å¡ij
    0.08
    说åĪ°
    0.08
    rz
    0.08
    Activations Density 0.038%

    No Known Activations