© 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. 14735
    Prev
    Next
    INDEX
    Explanations

    great place/value/gift/moments

    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
    ered
    -0.20
    yla
    -0.19
    gether
    -0.17
    GED
    -0.16
     Excellence
    -0.16
    大èĩ´
    -0.15
    edImage
    -0.15
    éĻIJãĤĬ
    -0.15
    ç«ĭãģ¦
    -0.15
    åĪ¶åº¦æĶ¹éĿ©
    -0.15
    POSITIVE LOGITS
    -grand
    0.28
    ness
    0.20
    fully
    0.20
    ÃŃsimo
    0.18
    -looking
    0.18
    ening
    0.18
    coat
    0.17
    rix
    0.17
    ification
    0.17
    bye
    0.16
    Activations Density 0.056%

    No Known Activations