© 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. 15814
    Prev
    Next
    INDEX
    Explanations

    numbers and sequences

    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
    è·
    -0.20
    _codegen
    -0.20
     Tanner
    -0.19
    .Sc
    -0.18
    urrent
    -0.18
    妲
    -0.18
    éĢĢ
    -0.18
     Mand
    -0.17
    ...(
    -0.17
    uer
    -0.17
    POSITIVE LOGITS
    è¿ĻéĩĮæľī
    0.22
    enders
    0.21
    åĥı个
    0.20
    æݧèĤ¡éĽĨåĽ¢
    0.20
    ìķµ
    0.20
    èĦĸ
    0.20
    ä¸Ģ大æĹ©
    0.20
    é²ľ
    0.19
    Ñīе
    0.19
    åĩ«
    0.19
    Activations Density 0.011%

    No Known Activations