© 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. 11241
    Prev
    Next
    INDEX
    Explanations

    forwarded from or to

    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
     Beaver
    -0.19
    çĹķ
    -0.18
    çīº
    -0.17
     minded
    -0.17
    cents
    -0.17
    çī¹çĤ¹æĺ¯
    -0.17
    纵è§Ĥ
    -0.17
    sgi
    -0.17
    ye
    -0.17
    aud
    -0.17
    POSITIVE LOGITS
    èĩ³
    0.23
    å¾·å°Ķ
    0.19
    nil
    0.19
    åĩºåİ»
    0.19
    ToFront
    0.18
    Dyn
    0.18
    è¿ĩæĿ¥
    0.18
    äºĨä¸Ģ份
    0.17
    ibly
    0.17
    æ¶Īæģ¯
    0.17
    Activations Density 0.010%

    No Known Activations