© 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. 16023
    Prev
    Next
    INDEX
    Explanations

    computer programs and systems

    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
    dro
    -0.23
    åºŃ
    -0.21
     bulb
    -0.20
    _RATIO
    -0.20
    chez
    -0.19
    tracked
    -0.19
    _FOLLOW
    -0.18
    æŁļ
    -0.18
    unan
    -0.18
    toy
    -0.18
    POSITIVE LOGITS
     IBM
    0.34
    IBM
    0.31
    .ibm
    0.29
    ç¨ĭåºı
    0.25
     programs
    0.24
     tapes
    0.23
    programs
    0.23
    ifax
    0.23
    idata
    0.23
    æŁľ
    0.23
    Activations Density 0.219%

    No Known Activations