© 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. 13986
    Prev
    Next
    INDEX
    Explanations

    corruption, charges, activist

    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
    hood
    -0.20
    /or
    -0.18
    åŃIJéĩĮ
    -0.18
    åįłæľīçİĩ
    -0.18
    forth
    -0.17
    meer
    -0.17
    åŁ
    -0.16
    orns
    -0.16
    ë¡Ŀ
    -0.16
     Terrace
    -0.15
    POSITIVE LOGITS
    ible
    0.23
    ulence
    0.21
    ä¸įåłª
    0.19
    icity
    0.19
    ibility
    0.19
    /dist
    0.19
    æĢ§çĸ¾çĹħ
    0.18
    ção
    0.18
    /in
    0.18
    Occurred
    0.17
    Activations Density 0.006%

    No Known Activations