© 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. 2644
    Prev
    Next
    INDEX
    Explanations

    technical system descriptors

    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
    äºĮåŃĹ
    -0.22
    áī¤
    -0.22
    aurus
    -0.20
    благо
    -0.20
    çij¾
    -0.19
    ä¸įçIJĨ
    -0.19
    емÑģÑı
    -0.19
    eldo
    -0.19
    UPI
    -0.19
    åĩ»
    -0.18
    POSITIVE LOGITS
    ç®Ģ称
    0.31
    æļ¨
    0.29
    以ä¸ĭç®Ģ称
    0.25
    ä¸ĭ称
    0.24
     sowie
    0.23
    raries
    0.23
    (NS
    0.22
    以åıĬ
    0.22
    (DB
    0.21
    æľīéĻIJåħ¬åı¸
    0.21
    Activations Density 2.775%

    No Known Activations