© 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. 11926
    Prev
    Next
    INDEX
    Explanations

    concepts of progress and function

    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
    è¿ĽåĨĽ
    -0.08
    æį
    -0.08
    inct
    -0.08
    å®Łãģ¯
    -0.08
    жив
    -0.08
    å³»
    -0.08
    讫
    -0.08
    é²ľæ´»
    -0.08
    ä¸Ģ缴åĪ°
    -0.08
    ober
    -0.08
    POSITIVE LOGITS
     çek
    0.08
    -notch
    0.08
    rough
    0.08
    icum
    0.07
    BOSE
    0.07
    æIJ¬è¿IJ
    0.07
    èµŀåĬ©
    0.07
     Rough
    0.07
    <quote
    0.07
    ielding
    0.07
    Activations Density 0.152%

    No Known Activations