© 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. 1660
    Prev
    Next
    INDEX
    Explanations

    fascinating things, ideas, or questions

    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
    -handed
    -0.26
    age
    -0.24
    manship
    -0.21
    -sided
    -0.20
    ish
    -0.20
    _warning
    -0.20
    wards
    -0.19
    份
    -0.19
    -fashioned
    -0.19
    liner
    -0.19
    POSITIVE LOGITS
    ively
    0.24
     creatures
    0.22
    æĹłæ¯Ķ
    0.20
    ened
    0.20
    arium
    0.19
    åĴĮæĶ¯æĮģ
    0.19
    ç¨ĭ度
    0.19
    ×ķ
    0.18
    fully
    0.18
    è¿©
    0.18
    Activations Density 0.009%

    No Known Activations