© 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. 2439
    Prev
    Next
    INDEX
    Explanations

    comprehensive explanations and assessments

    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
    chimp
    -0.23
    rees
    -0.23
    holm
    -0.22
     prominent
    -0.21
     fancy
    -0.21
    onz
    -0.21
    tres
    -0.21
    temps
    -0.21
    enberg
    -0.20
    oup
    -0.20
    POSITIVE LOGITS
    ible
    0.28
    ä½Ĩä¸įéĻIJäºİ
    0.25
    -minded
    0.25
    æĢ§çļĦ
    0.23
    atsu
    0.21
    ãģĿãĤĮãģ§
    0.21
    æĢ§
    0.20
    antee
    0.20
    æĢ§åĴĮ
    0.20
    orra
    0.20
    Activations Density 0.019%

    No Known Activations