© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12353
    Prev
    Next
    INDEX
    Explanations

    consideration

    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
    ega
    -0.19
    ey
    -0.19
    ynn
    -0.17
    sch
    -0.17
    éĵĽ
    -0.17
    sb
    -0.17
    ger
    -0.16
    ../../../
    -0.16
    rock
    -0.16
    arend
    -0.16
    POSITIVE LOGITS
    ably
    0.25
    ìĤ¬íķŃ
    0.22
    ors
    0.19
    ately
    0.19
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.18
     бÑĥмаг
    0.17
    able
    0.17
    æѤäºĭ
    0.17
     various
    0.16
     WHETHER
    0.16
    Activations Density 0.036%

    No Known Activations