© 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. 2334
    Prev
    Next
    INDEX
    Explanations

    coding context keywords

    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
    иÑĤелÑĮ
    -0.10
    详æĥħ
    -0.09
     اعت
    -0.09
    稿
    -0.09
    ainted
    -0.09
    еÑĩен
    -0.08
    çģ¶
    -0.08
    Ñīен
    -0.08
    ened
    -0.08
    allah
    -0.08
    POSITIVE LOGITS
    æ´Ļ
    0.10
     Claude
    0.09
    èĽ®
    0.08
    åįģ足
    0.08
    овÑĭй
    0.08
    cy
    0.08
    stri
    0.08
    è¿Ļ个è¯į
    0.08
    iere
    0.08
    å®ĺ
    0.07
    Activations Density 0.342%

    No Known Activations