© 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. 12160
    Prev
    Next
    INDEX
    Explanations

    opening quotation marks

    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
    æĪijä¸įæĥ³
    -0.27
    å¸ĥ
    -0.19
    èĤ¡
    -0.19
    >:</
    -0.18
    pheres
    -0.18
    æİ©
    -0.18
    åł°
    -0.18
    æĪijåıĪ
    -0.18
    IRST
    -0.18
     others
    -0.17
    POSITIVE LOGITS
    ecer
    0.19
    该éĻ¢
    0.19
    rys
    0.19
    è¹Ĵ
    0.19
    Perl
    0.19
    alian
    0.19
    çķħéĢļ
    0.19
    Ñij
    0.19
    .Elements
    0.18
    éĢłè¡Ģ
    0.18
    Activations Density 0.065%

    No Known Activations