© 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. 20905
    Prev
    Next
    INDEX
    Explanations

    in need or urgent requirements

    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
    å°ıå°ıçļĦ
    -0.09
    ä»İ容
    -0.09
    _OVERFLOW
    -0.08
    æݪ
    -0.08
     Doug
    -0.08
    ç¢Ĺ
    -0.08
    anning
    -0.08
    plevel
    -0.08
    è¿Ŀæ³ķè¡Į为
    -0.08
    oproject
    -0.08
    POSITIVE LOGITS
    éľĢè¦ģ
    0.15
    æĢ¥éľĢ
    0.15
    need
    0.14
     нÑĥж
    0.14
     need
    0.14
     cần
    0.13
    _need
    0.13
    è¿«åĪĩ
    0.13
     besoin
    0.13
    äºŁ
    0.13
    Activations Density 0.023%

    No Known Activations