© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15080
    Prev
    Next
    INDEX
    Explanations

    food and dining establishments

    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
    èĢģåħ¬
    -0.20
    æ¶İ
    -0.20
    åľ¨æĪijåĽ½
    -0.20
    渺
    -0.20
    碰
    -0.20
    ÃŁer
    -0.20
    å¼Ģæ°´
    -0.19
    èĢģåŃĹåı·
    -0.19
    çĻ¾äº¿
    -0.19
    theid
    -0.19
    POSITIVE LOGITS
    éħį
    0.20
     projectile
    0.19
    éħįä¸Ĭ
    0.19
    side
    0.19
     ballot
    0.19
    LTE
    0.19
    æ£ĭ
    0.18
    åı¯ä¾Ľ
    0.17
    å°±å¼Ģå§ĭ
    0.17
    chor
    0.17
    Activations Density 0.021%

    No Known Activations