© 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. 18116
    Prev
    Next
    INDEX
    Explanations

    means for

    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
    -0.12
    涯
    -0.12
    涧
    -0.10
    åĩ¹
    -0.08
    dress
    -0.08
    çŁ¥æĥħ
    -0.08
    å·¨
    -0.08
     glance
    -0.08
    izable
    -0.08
    å°»
    -0.08
    POSITIVE LOGITS
    èĢ³è¾¹
    0.10
    ä¸Ģå¥Ĺ
    0.09
    æݧ
    0.09
    å°ıå§IJå§IJ
    0.09
    æŀ¶æŀĦ
    0.08
    थ
    0.08
    ç³»ç»ŁçļĦ
    0.08
    çĨĬçĮ«
    0.08
     dise
    0.08
    agens
    0.08
    Activations Density 0.404%

    No Known Activations