© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52411
    Prev
    Next
    INDEX
    Explanations

    extra cost

    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
    æ¯Ķäºļ
    -0.09
    multipart
    -0.09
    å°½åı¯èĥ½
    -0.09
    BITS
    -0.08
    æĮ¤
    -0.08
    主è¦ģçĶ¨äºİ
    -0.08
    åį¯
    -0.08
    é¡¿
    -0.08
    åº
    -0.08
    à¹Ģà¸Ļ
    -0.08
    POSITIVE LOGITS
    åı¦è¡Į
    0.19
    é¢Ŀå¤ĸ
    0.18
     additional
    0.15
     thêm
    0.14
    åı¦å¤ĸ
    0.14
    additional
    0.13
    _extra
    0.13
    Additional
    0.13
     Additional
    0.12
     extra
    0.12
    Activations Density 0.042%

    No Known Activations