© 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. 13784
    Prev
    Next
    INDEX
    Explanations

    or unchanged compared

    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
    ä¸įä»ħæĺ¯
    -0.21
    裸
    -0.21
    ä¸įåĨįæĺ¯
    -0.21
    è¾Ĭ
    -0.20
    åĬłæĮģ
    -0.19
    åıªéľĢ
    -0.19
    çĤĶ
    -0.19
    ä¸įä»ħä»ħæĺ¯
    -0.19
    sole
    -0.19
     Alvarez
    -0.19
    POSITIVE LOGITS
    æĮģå¹³
    0.26
    å®ľå±ħ
    0.23
    è¹Ī
    0.23
    itched
    0.21
    æĢ»ä½ĵ
    0.20
    åįģ大
    0.18
    æĿŃ
    0.18
    ä¸Ģæł·
    0.18
    é£ŀæī¬
    0.18
    zing
    0.18
    Activations Density 0.195%

    No Known Activations