© 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. 3887
    Prev
    Next
    INDEX
    Explanations

    setting up clauses with which

    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
    ç½ijç»ľæ¸¸æĪı
    -0.10
    autical
    -0.10
     Ä°n
    -0.10
    chter
    -0.09
    åľ¨è¿Ļ个
    -0.09
    .childNodes
    -0.09
    çĿij
    -0.09
    åľ¨è¿ĻéĩĮ
    -0.09
    æIJ¬åĪ°
    -0.09
    为ä»Ģä¹Īä¸į
    -0.09
    POSITIVE LOGITS
    èķ´
    0.09
    èįĨå·ŀ
    0.09
    æݺ
    0.09
    ÑĨиÑİ
    0.09
    央
    0.08
     confl
    0.08
    æ³Ħ
    0.08
    躺
    0.08
    æ¯ķä¸ļåIJİ
    0.08
    dojo
    0.08
    Activations Density 0.284%

    No Known Activations