© 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. 2953
    Prev
    Next
    INDEX
    Explanations

    issue or problem

    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
    åĽĽæĸ¹
    -0.25
    æŁ¥
    -0.24
    æıIJ款
    -0.23
    formed
    -0.23
    eway
    -0.23
    pent
    -0.22
     Fool
    -0.22
    åıįå¼¹
    -0.22
    ç»ĵæĿŁäºĨ
    -0.22
     Opp
    -0.22
    POSITIVE LOGITS
     issue
    0.31
    éĹ®é¢ĺæĺ¯
    0.30
    éĹ®é¢ĺ
    0.28
    Issue
    0.26
     Issue
    0.25
    _issue
    0.23
     problem
    0.23
    åķıé¡Į
    0.23
     Scaffold
    0.23
    åĮ»æĬ¤
    0.23
    Activations Density 0.190%

    No Known Activations