© 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. 58596
    Prev
    Next
    INDEX
    Explanations

    Dab

    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
    west
    -0.09
    à¹Į
    -0.08
    æŶè£ħ
    -0.08
    å¼¼
    -0.08
    stad
    -0.08
    ance
    -0.08
    VERBOSE
    -0.08
    elry
    -0.08
    orth
    -0.08
    ustr
    -0.08
    POSITIVE LOGITS
    bé
    0.11
    åĹĴ
    0.10
    luck
    0.09
     INCLUDED
    0.09
     Ecc
    0.09
     Redistributions
    0.09
    èģĬèģĬ
    0.09
    ¡°
    0.09
    羡
    0.09
    é¢ĨåŁŁ
    0.08
    Activations Density 0.008%

    No Known Activations