© 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. 49717
    Prev
    Next
    INDEX
    Explanations

    % or percentage

    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
    éªIJ
    -0.09
    UPPORT
    -0.08
    ä¸į便
    -0.08
    ãĥĥãĤ¯
    -0.08
    çĤ¹éĴŁ
    -0.08
    .stub
    -0.08
    åı«å£°
    -0.08
     Rath
    -0.08
    æ¼ĵ
    -0.08
    Ñĩа
    -0.08
    POSITIVE LOGITS
    alse
    0.10
    é¾
    0.10
    çĻ¾åĪĨä¹ĭ
    0.09
    æłħ
    0.09
    è¦ĨçĽĸçİĩ
    0.08
    åľ¨æķ´ä¸ª
    0.08
     (%)
    0.08
    .ua
    0.08
    ILED
    0.08
    以ä¸ĬçļĦ
    0.08
    Activations Density 0.169%

    No Known Activations