© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53019
    Prev
    Next
    INDEX
    Explanations

    carefully selected or planned

    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
    横åIJij
    -0.09
    çĺ°
    -0.09
    åģļæ³ķ
    -0.08
    æī¿åıĹ
    -0.08
    æŀ¯çĩ¥
    -0.08
    æŁIJç§įç¨ĭ度
    -0.08
    edar
    -0.08
    ooter
    -0.08
     tats
    -0.08
     Linden
    -0.08
    POSITIVE LOGITS
    å°ıå¿ĥ
    0.14
    æħİéĩį
    0.13
     carefully
    0.13
    ç»Ĩèĩ´
    0.12
     careful
    0.11
    æ¯ıä¸Ģ个
    0.10
    æ¯ıä¸Ģ
    0.10
    è°¨æħİ
    0.10
     từng
    0.10
     detail
    0.10
    Activations Density 0.045%

    No Known Activations