© 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. 11378
    Prev
    Next
    INDEX
    Explanations

    deciding between options

    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
    ä¼ī
    -0.20
    çłĶ究éĻ¢
    -0.20
    éŁ©åĽ½
    -0.20
    累累
    -0.19
    TRACE
    -0.19
    Independ
    -0.19
    追溯
    -0.19
     staple
    -0.18
    ev
    -0.18
    éļĶéŁ³
    -0.18
    POSITIVE LOGITS
    è¿Łè¿Ł
    0.34
    çĬ¹è±«
    0.27
    åĥµ
    0.26
     paralysis
    0.25
    éĢ¡
    0.24
    æīģ
    0.23
     hesitation
    0.22
    æĬīæĭ©
    0.21
    ä¸įç¡®å®ļ
    0.21
    æ··ä¹±
    0.21
    Activations Density 0.074%

    No Known Activations