© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26129
    Prev
    Next
    INDEX
    Explanations

    porch, deck, steps, doorstep, veranda

    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
    Negative Logits
    utow
    -0.10
    èĨ³
    -0.09
     Barcl
    -0.09
    ä»İ严
    -0.09
    åºĹåĨħ
    -0.08
    è¡Įä¸ļåĨħ
    -0.08
    åĩºåľº
    -0.08
    èįĩ
    -0.08
    çľ¼æ³ª
    -0.08
    èĩªç§ģ
    -0.08
    POSITIVE LOGITS
    iers
    0.11
     vá»±c
    0.10
    _RAM
    0.09
     sá»ķ
    0.09
    icit
    0.09
    ä¸ĬçļĦ
    0.08
    gang
    0.08
    强大çļĦ
    0.08
    ier
    0.08
    ä¸Ĭæľī
    0.08
    Activations Density 0.005%

    No Known Activations