© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52113
    Prev
    Next
    INDEX
    Explanations

    private key or private space

    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
    ding
    -0.11
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.11
    InProgress
    -0.10
    animations
    -0.09
    sey
    -0.09
    é»İæĺİ
    -0.09
     thức
    -0.09
    xin
    -0.09
    PerPixel
    -0.09
     dõi
    -0.09
    POSITIVE LOGITS
     readonly
    0.12
    zza
    0.10
     Äijáo
    0.10
    ÑģÑĮ
    0.09
    ity
    0.09
    -looking
    0.09
    -sector
    0.09
    agens
    0.09
    æµ·æ¹¾
    0.09
    eger
    0.09
    Activations Density 0.039%

    No Known Activations