© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11897
    Prev
    Next
    INDEX
    Explanations

    words like hate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    ERO
    -0.17
    ä¸įåĩº
    -0.17
    mente
    -0.17
    ãģ¨ãĤĬãģĤ
    -0.16
    hone
    -0.16
    еÑĩение
    -0.16
    iment
    -0.16
    itional
    -0.15
    IRM
    -0.15
    éªĮæĶ¶
    -0.15
    POSITIVE LOGITS
    fully
    0.30
    fulness
    0.23
    ful
    0.20
    lessly
    0.19
    ess
    0.18
    eful
    0.18
    ably
    0.18
    FUL
    0.17
    ulous
    0.17
    ened
    0.17
    Activations Density 0.008%

    No Known Activations