© 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. 31074
    Prev
    Next
    INDEX
    Explanations

    't contracts

    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
    sted
    -0.10
    ective
    -0.10
    åĽ½æ°ijç»ıæµİ
    -0.09
    èıľ
    -0.09
    èµĤ
    -0.08
    æĹ¥åŃIJ
    -0.08
    ä¸Ńåįİ
    -0.08
     иÑģÑĤ
    -0.08
    髹
    -0.08
    åĶ¤
    -0.08
    POSITIVE LOGITS
    é¹°
    0.09
    马æĭī
    0.08
    æĻº
    0.08
    tsx
    0.08
    eon
    0.08
    onical
    0.08
    wise
    0.08
    ترÙĪ
    0.08
    onium
    0.08
    inar
    0.07
    Activations Density 0.070%

    No Known Activations