© 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. 16454
    Prev
    Next
    INDEX
    Explanations

    love and care for others

    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
    æĸ°æł¼å±Ģ
    -0.21
    æİ
    -0.21
    æľīåħ³éĥ¨éŨ
    -0.21
    åħį
    -0.20
    èĪĨ论
    -0.19
     rval
    -0.19
    壮è§Ĥ
    -0.19
    å¤ĸåĽ´
    -0.19
    ook
    -0.18
    omy
    -0.18
    POSITIVE LOGITS
    åľ¨ä¹İ
    0.27
    çĥŃçĪ±
    0.23
     оÑĤноÑĪении
    0.23
    ä½ĵè´´
    0.22
    è¯ļæĦı
    0.22
    /widget
    0.21
     concern
    0.21
    seau
    0.21
    åħ³å¿ĥ
    0.21
    ä¹ĭæĥħ
    0.20
    Activations Density 0.067%

    No Known Activations