© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1118
    Prev
    Next
    INDEX
    Explanations

    names

    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
    æŁĬ
    -0.27
    åļĨ
    -0.27
    ä¾´
    -0.26
    ois
    -0.25
    家åĸ»
    -0.25
    â½Ĵ
    -0.24
    峧
    -0.23
    Abs
    -0.23
    amework
    -0.23
    è½·
    -0.23
    POSITIVE LOGITS
    æł¹
    0.31
     J
    0.28
    å¾·
    0.28
     K
    0.27
     kw
    0.27
     roots
    0.26
    åĿļ
    0.26
    ç»´
    0.26
    èĹı
    0.26
    è½®
    0.25
    Activations Density 0.264%

    No Known Activations