© 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. 13543
    Prev
    Next
    INDEX
    Explanations

    ive / ative

    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
    ãģĦãģ¾ãģĻ
    -0.25
    ings
    -0.23
    lo
    -0.22
    ship
    -0.22
    ed
    -0.21
    ยา
    -0.21
    spot
    -0.21
    line
    -0.20
    ships
    -0.20
    making
    -0.20
    POSITIVE LOGITS
    -minded
    0.30
     minded
    0.25
    ity
    0.25
    -looking
    0.22
    ITY
    0.22
    y
    0.22
    æĢ§å¼º
    0.21
    yat
    0.20
    zza
    0.20
    -thinking
    0.19
    Activations Density 0.249%

    No Known Activations