© 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. 11346
    Prev
    Next
    INDEX
    Explanations

    exclamations of annoyance

    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
    lik
    -0.20
    æī®
    -0.19
    访
    -0.19
    åĵ©
    -0.19
    çĵ®
    -0.19
    bor
    -0.18
    ç¿©
    -0.18
    ClassName
    -0.18
    寺
    -0.18
     Abdel
    -0.18
    POSITIVE LOGITS
    apy
    0.19
    ɳ
    0.18
    etically
    0.18
     Achilles
    0.17
     Ner
    0.17
    IBUTES
    0.17
    errupted
    0.17
    canf
    0.17
    põe
    0.17
     Millenn
    0.16
    Activations Density 0.011%

    No Known Activations