© 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. 62078
    Prev
    Next
    INDEX
    Explanations

    date or time of event

    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
    æĪĸå¤ļ
    -0.08
    ieg
    -0.08
    AVING
    -0.08
    Looper
    -0.08
    æĮ¡
    -0.08
    é¢Ĩ导人
    -0.08
    -ed
    -0.08
    è½±
    -0.08
    åħ¶å®ŀå°±æĺ¯
    -0.07
     drip
    -0.07
    POSITIVE LOGITS
    ä½¥
    0.09
    lish
    0.09
    intr
    0.09
    çŃ¾åŃĹ
    0.09
    ä¼ł
    0.09
    arness
    0.08
    ä¸Ģ樣
    0.08
    çŃ¾
    0.08
    atcher
    0.08
     BOTTOM
    0.08
    Activations Density 0.008%

    No Known Activations