© 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. 53436
    Prev
    Next
    INDEX
    Explanations

    Free Software Foundation

    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°±è¿Ļæł·
    -0.09
    èħ´
    -0.08
    迤
    -0.08
    utom
    -0.08
    æĿµ
    -0.08
    occo
    -0.08
     tap
    -0.08
    æĵ¢
    -0.08
    ifter
    -0.08
    æľĪä¸ĭ
    -0.08
    POSITIVE LOGITS
    WARE
    0.09
    _symbols
    0.09
    åīįåı°
    0.09
     Bender
    0.09
    ertz
    0.09
    åĮ»åĬ¡
    0.09
    åħĶ
    0.09
    iske
    0.09
     Symbols
    0.09
    dden
    0.09
    Activations Density 0.246%

    No Known Activations