© 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. 15904
    Prev
    Next
    INDEX
    Explanations

    competition outcomes

    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
    éļıçĿĢæŶéĹ´
    -0.23
    å¹´ä¹ĭ
    -0.19
    ewing
    -0.19
    èĤĩäºĭ
    -0.19
    _RW
    -0.19
    å¸ģ
    -0.19
     lately
    -0.19
     railing
    -0.19
    大çĽĺ
    -0.19
    èľĵ
    -0.18
    POSITIVE LOGITS
    æ·ĺæ±°
    0.32
    æĻĭ级
    0.29
    çģŃ
    0.28
    è¿Ľåħ¥
    0.26
    è¿Ľåħ¥åĪ°
    0.24
    elim
    0.24
    被æ·ĺæ±°
    0.23
    åĪĿæŃ¥
    0.23
     elimination
    0.22
    éĢ²åħ¥
    0.22
    Activations Density 0.060%

    No Known Activations