© 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. 1533
    Prev
    Next
    INDEX
    Explanations

    what makes

    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
    åı¯çĸij
    -0.33
     abort
    -0.33
    åħ¬çĦ¶
    -0.33
    åıĸæ¶Ī
    -0.31
     Worse
    -0.30
    诡å¼Ĥ
    -0.30
    è¹Ĭ
    -0.30
     abruptly
    -0.29
    åı¦è¡Į
    -0.29
     dubious
    -0.29
    POSITIVE LOGITS
    å¥īçĮ®
    0.40
    å¹³åĩ¡
    0.39
    åĽŀé¦Ī
    0.38
    幸ç¦ıæĦŁ
    0.37
     empowerment
    0.36
     nurt
    0.36
    æĪIJå°±æĦŁ
    0.36
     passion
    0.36
    æŃ£èĥ½éĩı
    0.35
    æ¯ı个人
    0.35
    Activations Density 0.085%

    No Known Activations