© 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. 61245
    Prev
    Next
    INDEX
    Explanations

    disappointed / didn't / missed

    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
    æij¸ç´¢
    -0.10
    æİĩ
    -0.10
    çģ¾åĮº
    -0.10
    моÑĤ
    -0.10
    å¾Ĺ天
    -0.09
    holm
    -0.09
    _rights
    -0.09
    梯
    -0.09
    åıįèħIJ
    -0.09
    èļģ
    -0.09
    POSITIVE LOGITS
    ç«ŁçĦ¶
    0.12
    没èĥ½
    0.12
    å±ħçĦ¶
    0.10
    è½»æĺĵ
    0.10
    è¾ľè´Ł
    0.09
    çľĭä¸įåĪ°
    0.09
    ä¸įè§ģ
    0.09
    éģĹæĨ¾
    0.09
     limiting
    0.08
    åľ¨çº¿åĴ¨è¯¢
    0.08
    Activations Density 0.048%

    No Known Activations