© 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. 2573
    Prev
    Next
    INDEX
    Explanations

    real pain or pleasure

    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
    çļĦæŶéĹ´éĩĮ
    -0.26
    æĪĸèĢħ说
    -0.25
    æĽ´å¤ļçļĦ
    -0.25
    ospace
    -0.23
    ä»»ä½ķæŶåĢĻ
    -0.23
    ús
    -0.23
    æ²»çĸĹæĸ¹æ³ķ
    -0.23
     relating
    -0.23
    çľĭå¾ħ
    -0.22
     responding
    -0.22
    POSITIVE LOGITS
     witness
    0.25
     surprise
    0.24
    å¥ĩ迹
    0.24
     surprises
    0.24
     bott
    0.24
    ç¦ģå¿Į
    0.23
     stubborn
    0.23
    inely
    0.23
     ÑģÑĤо
    0.23
     wow
    0.22
    Activations Density 0.016%

    No Known Activations