© 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. 27304
    Prev
    Next
    INDEX
    Explanations

    http or https followed by slashes

    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
    å®Ľ
    -0.10
    blogs
    -0.10
    .trace
    -0.09
     INDIRECT
    -0.09
    ç»ķ
    -0.09
    åĶĨ
    -0.09
    æľķ
    -0.09
    åłµ
    -0.08
    lord
    -0.08
    æķ£
    -0.08
    POSITIVE LOGITS
    æĺı
    0.09
    æ·±åĪĩ
    0.08
     enumeration
    0.08
    å¿ĥè·³
    0.08
    åIJĿ
    0.07
    æį»
    0.07
    å·¢
    0.07
    æħ·æħ¨
    0.07
     Westminster
    0.07
    鹧
    0.07
    Activations Density 0.004%

    No Known Activations