© 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. 2767
    Prev
    Next
    INDEX
    Explanations

    production, consistency, speed

    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
    Instrument
    -0.24
    çĶ¨äºİ
    -0.24
    çĶ¨éĢĶ
    -0.23
    åijĨ
    -0.23
     Hä
    -0.23
    ä»ĸèĩªå·±
    -0.23
     moderne
    -0.23
    ä¸ļ
    -0.23
    æĸŁ
    -0.23
    à¸ģระà¸ļ
    -0.23
    POSITIVE LOGITS
     inconsist
    0.29
     consistently
    0.28
    éĵ±
    0.27
     consistency
    0.25
     uneven
    0.25
     inconsistencies
    0.25
     inconsistency
    0.25
     inconsistent
    0.24
     consistent
    0.24
     during
    0.24
    Activations Density 0.012%

    No Known Activations