© 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. 2099
    Prev
    Next
    INDEX
    Explanations

    conflict and its contexts

    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
    ning
    -0.22
    psilon
    -0.20
    infeld
    -0.19
    covery
    -0.19
    coming
    -0.18
    iac
    -0.18
    NING
    -0.18
    åı¯æĥľ
    -0.18
    ä¸ľè¥¿
    -0.18
    vig
    -0.18
    POSITIVE LOGITS
    uous
    0.26
    ions
    0.24
    ive
    0.23
    æĢ§å¼º
    0.23
    ÑĥÑİÑī
    0.23
    -minded
    0.22
    uate
    0.22
    shire
    0.22
    buster
    0.21
     minded
    0.21
    Activations Density 0.007%

    No Known Activations