© 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. 11949
    Prev
    Next
    INDEX
    Explanations

    need of

    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
    åŃĺåľ¨äºİ
    -0.20
    walker
    -0.19
    /is
    -0.18
    à¸ģารà¸Ĺำà¸ĩาà¸Ļ
    -0.18
    çĵ¶åŃIJ
    -0.18
    ç²¾åĬĽ
    -0.18
    æĹ©æĻļ
    -0.17
    çł»
    -0.17
    icipation
    -0.17
     suicides
    -0.17
    POSITIVE LOGITS
    ç¨ĭ度
    0.20
    iben
    0.18
    è´¢
    0.18
    å·²ä¹ħ
    0.18
    -of
    0.18
    reau
    0.17
    repid
    0.17
    bourg
    0.17
    lier
    0.17
    cue
    0.17
    Activations Density 0.009%

    No Known Activations