© 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. 54434
    Prev
    Next
    INDEX
    Explanations

    began, started, continues

    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
    åħ¨ç¨ĭ
    -0.08
    RIX
    -0.08
     Claim
    -0.08
    æĦı大
    -0.08
    èĩ
    -0.08
     поддеÑĢжива
    -0.08
    addChild
    -0.08
     CLAIM
    -0.08
    åľ°è¯´
    -0.08
    è°ļ
    -0.07
    POSITIVE LOGITS
    éĻį临
    0.11
    åħ´æĹº
    0.10
    ä¸įå°½
    0.10
    ä¸įä¸Ģæł·çļĦ
    0.09
    imi
    0.09
    羣çļĦå¾Ī
    0.09
    大家
    0.09
    åĩºçİ°éĹ®é¢ĺ
    0.08
    éĵº
    0.08
    大è¡Ĺ
    0.08
    Activations Density 0.040%

    No Known Activations