© 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. 1115
    Prev
    Next
    INDEX
    Explanations

    be followed by it or careful or beauty

    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
    naire
    -0.25
    keit
    -0.22
    ISED
    -0.19
     ÐIJлекÑģан
    -0.18
    esi
    -0.18
    iento
    -0.18
    ses
    -0.18
    æĬĬæĮģ
    -0.18
    ation
    -0.17
     пÑĥÑĤеÑĪ
    -0.17
    POSITIVE LOGITS
    ings
    0.30
    çĦ¶æĺ¯
    0.27
    autiful
    0.27
    ters
    0.25
    -être
    0.25
    bbe
    0.24
    INGS
    0.24
    aways
    0.24
    ingly
    0.24
    structions
    0.23
    Activations Density 0.037%

    No Known Activations