© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 2660
    Prev
    Next
    INDEX
    Explanations

    suffix 's

    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
     declined
    -0.24
    çļĦä¸įåIJĮ
    -0.24
    çĶļèĩ³è¿ĺ
    -0.24
    -Oct
    -0.23
    _but
    -0.23
     tallest
    -0.23
    -Dec
    -0.23
     Cyrus
    -0.22
    DECL
    -0.22
     declining
    -0.22
    POSITIVE LOGITS
     nonetheless
    0.42
     nevertheless
    0.36
    çijķ
    0.33
     dang
    0.32
     darn
    0.32
    oner
    0.26
     damn
    0.25
    èĻĶ
    0.25
     perse
    0.24
     fulfilling
    0.24
    Activations Density 0.146%

    No Known Activations