© 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. 16029
    Prev
    Next
    INDEX
    Explanations

    out there

    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
    ãģ¯ãģĺãĤģ
    -0.20
    Ñģ
    -0.18
    潮湿
    -0.18
    æѤå¤ĸ
    -0.17
    èģĮåĬ¡
    -0.17
    cassert
    -0.17
    sen
    -0.17
    son
    -0.17
    ãĤĥ
    -0.16
    约è°Ī
    -0.16
    POSITIVE LOGITS
    /down
    0.21
    iny
    0.19
    éľīç´ł
    0.18
    ledon
    0.18
    isclosed
    0.18
    é»Ķ
    0.18
    isd
    0.17
    çĮ·
    0.17
    ETER
    0.17
    -facing
    0.17
    Activations Density 0.006%

    No Known Activations