© 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. 50648
    Prev
    Next
    INDEX
    Explanations

    assorted, bold, deals, get, free

    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·ĭ
    -0.10
    èĭķ
    -0.09
    ä¾ĽåĽ¾
    -0.09
    ÑĩиÑĤ
    -0.09
    çİĭåŃIJ
    -0.08
    ä½Ł
    -0.08
    çł¾
    -0.08
    åĶĩ
    -0.08
    ä¾Ŀ次
    -0.08
     dust
    -0.08
    POSITIVE LOGITS
    antha
    0.09
    å·¥ç¨ĭæľºæ¢°
    0.09
    Intro
    0.09
    æ°Ķè´¨
    0.09
    tle
    0.09
    å°Ĭ
    0.09
    .EXTRA
    0.08
    arden
    0.08
    _algo
    0.08
    確ãģĭ
    0.08
    Activations Density 0.001%

    No Known Activations