© 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. 14635
    Prev
    Next
    INDEX
    Explanations

    car brands and tyres

    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
    åī§
    -0.21
    åĬ¨éĿĻ
    -0.20
     gyr
    -0.19
    æĤ¨çļĦåŃ©åŃIJ
    -0.19
    _fraction
    -0.19
    å¿µä½Ľ
    -0.19
    éĤĽ
    -0.19
    DDD
    -0.18
    jej
    -0.18
    èµĦè´¨
    -0.18
    POSITIVE LOGITS
    ResponseStatus
    0.20
    amura
    0.19
     singular
    0.19
    kees
    0.19
    çīĽ
    0.19
    amina
    0.18
    arez
    0.18
     rival
    0.18
    nock
    0.18
    /apple
    0.17
    Activations Density 0.008%

    No Known Activations