© 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. 1581
    Prev
    Next
    INDEX
    Explanations

    Iranian names and medical terms

    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
    alist
    -0.09
    æĸ°å¹´
    -0.09
    OLER
    -0.08
    è´»
    -0.08
    chten
    -0.08
    çģ¼
    -0.08
    æĸ°çļĦä¸Ģå¹´
    -0.08
    èIJ¥ä¸ļ
    -0.08
    æ³±
    -0.08
    çĩŁ
    -0.08
    POSITIVE LOGITS
    æł¸å®ļ
    0.09
    mol
    0.09
     warp
    0.08
    ominated
    0.08
    .Panel
    0.08
    _war
    0.08
    agos
    0.08
    iar
    0.08
    .SDK
    0.08
    个æĢ§
    0.08
    Activations Density 0.003%

    No Known Activations