© 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. 2053
    Prev
    Next
    INDEX
    Explanations

    impression or impressed

    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
    对人ä½ĵ
    -0.22
    æĻļæĬ¥
    -0.21
    redo
    -0.21
    ----------------------------------------------------------------------------
    -0.20
    ebra
    -0.19
    indre
    -0.19
    社ä¼ļä¿ĿéĻ©
    -0.19
    ä¸įèĤ¯
    -0.19
    åı¸ä»¤
    -0.18
    ì§ľ
    -0.18
    POSITIVE LOGITS
    ively
    0.27
    ments
    0.23
    ive
    0.23
    sed
    0.23
    ses
    0.22
    -taking
    0.21
    pective
    0.21
    maker
    0.21
    ible
    0.20
    eur
    0.20
    Activations Density 0.009%

    No Known Activations