© 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. 34353
    Prev
    Next
    INDEX
    Explanations

    location names ending in 's'

    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
    fen
    -0.09
    le
    -0.08
    sect
    -0.08
    ly
    -0.08
    lette
    -0.08
    Ken
    -0.07
    val
    -0.07
    å£ģåŀĴ
    -0.07
     Valley
    -0.07
     spinning
    -0.07
    POSITIVE LOGITS
    ampler
    0.10
    京津åĨĢ
    0.10
    åĩ¡äºĭ
    0.10
    åį·
    0.10
    鸱
    0.10
    éĤ¢
    0.10
    åĸĻ
    0.09
    åµĩ
    0.09
    æ´İ
    0.09
     wcs
    0.09
    Activations Density 0.022%

    No Known Activations