© 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. 18919
    Prev
    Next
    INDEX
    Explanations

    laid out or laid down

    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
    æĮĤ
    -0.11
    åIJ¹
    -0.10
    stable
    -0.09
     hak
    -0.08
    legg
    -0.08
    æİĽ
    -0.08
    ä¸Ģ家
    -0.08
     Terrain
    -0.08
    å¤ļ家
    -0.08
    åŀĭä¼ģä¸ļ
    -0.08
    POSITIVE LOGITS
    ammer
    0.12
    æµĵåİļ
    0.10
    æĺİæĺİ
    0.09
    éĤ¸
    0.09
    ormal
    0.09
    èĪĴå¿ĥ
    0.09
    ä¸Ģéģĵ
    0.09
    pager
    0.08
    æŁĶåĴĮ
    0.08
    QUIRE
    0.08
    Activations Density 0.019%

    No Known Activations