© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2605
    Prev
    Next
    INDEX
    Explanations

    quality of management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    confirmed
    -0.23
    isd
    -0.23
     hoped
    -0.23
    ä¸Ģ身
    -0.23
    LICENSE
    -0.22
     confirmed
    -0.22
    preferred
    -0.22
     preferred
    -0.22
     ges
    -0.22
     powerful
    -0.22
    POSITIVE LOGITS
    管çIJĨæ°´å¹³
    0.40
    对å¾ħ
    0.35
    è¿ĺä¸įå¦Ĥ
    0.34
    管çIJĨä½ĵåĪ¶
    0.34
    æľįåĬ¡è´¨éĩı
    0.34
    ç³Łç³ķ
    0.33
    å·¥ä½ľä½ľé£İ
    0.33
     quality
    0.32
    è´¨éĩıåĴĮ
    0.32
    以èĩ³äºİ
    0.32
    Activations Density 0.154%

    No Known Activations