© 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. 20302
    Prev
    Next
    INDEX
    Explanations

    release or let go

    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
    æĭĬ
    -0.11
    çģ¸
    -0.10
    èĩ³ä¸Ĭ
    -0.09
    笳
    -0.09
    æİ¥è¿ij
    -0.09
    ä¿Ŀå¯Ĩ
    -0.09
    åı°ä¸Ĭ
    -0.09
    Ñģка
    -0.09
    ç»ıéªĮåĢ¼
    -0.09
    éĺľ
    -0.09
    POSITIVE LOGITS
    æĶ¾æīĭ
    0.12
    èĩªå¦Ĥ
    0.09
    .release
    0.09
    æĶ¾è¿ĩ
    0.09
    /release
    0.09
    CCCCCC
    0.09
    æĶ¾æĿ¾
    0.09
    /releases
    0.09
    æĶ¾å®½
    0.08
    Seat
    0.08
    Activations Density 0.053%

    No Known Activations