© 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. 62289
    Prev
    Next
    INDEX
    Explanations

    companies and services

    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
    ç£ķ
    -0.11
    idor
    -0.10
    å¼¼
    -0.10
    é¢ĩ为
    -0.10
    è¿·èĮ«
    -0.10
    çĻ¾è´§
    -0.10
    çľ¼åīįçļĦ
    -0.10
    é£ı
    -0.09
    碰
    -0.09
    çīĩåĪ»
    -0.09
    POSITIVE LOGITS
    gt
    0.09
    çħ§
    0.08
    rone
    0.08
    isl
    0.08
    arde
    0.07
     tracked
    0.07
    gd
    0.07
    æ°´æĻ¶
    0.07
    zag
    0.07
    ury
    0.07
    Activations Density 0.004%

    No Known Activations