© 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. 10908
    Prev
    Next
    INDEX
    Explanations

    Dalbem, Alcasid, Balbontin, Ferro, Hart, Albrecht, Cotton, Balseiro

    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
    upo
    -0.18
    ÑģÑĤи
    -0.18
    ble
    -0.17
    shal
    -0.17
    ively
    -0.17
    illard
    -0.17
    ned
    -0.17
    æĢ§å¼º
    -0.17
    åªĽ
    -0.17
    æĪ¶
    -0.16
    POSITIVE LOGITS
    orado
    0.19
    onso
    0.18
    amation
    0.18
    çĵ·
    0.17
    idan
    0.16
    arity
    0.16
    èij¬
    0.16
    ades
    0.16
    oS
    0.16
    讳
    0.16
    Activations Density 0.296%

    No Known Activations