© 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. 35690
    Prev
    Next
    INDEX
    Explanations

    arrested or taken

    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
    æĿĢæīĭ
    -0.09
    lick
    -0.09
    缩å°ı
    -0.09
    æµĨ
    -0.09
    缩
    -0.09
    çŀĦåĩĨ
    -0.08
    éĵį
    -0.08
    ç®ĢåĮĸ
    -0.08
    èĪ«
    -0.08
     HAPP
    -0.08
    POSITIVE LOGITS
    ç«ĭåį³
    0.10
    ä¸Ģå¤ľ
    0.10
    å«Įçĸij人
    0.09
    ç»
    0.09
    ç«ĭ马
    0.09
    æ¶īå«Į
    0.09
    <?,
    0.09
    çİ°åľº
    0.08
     assist
    0.08
    é©»æĿij
    0.08
    Activations Density 0.046%

    No Known Activations