© 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. 13918
    Prev
    Next
    INDEX
    Explanations

    Q: / DESCRIPTION: / Share

    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
    tal
    -0.22
    å¾ĹçĽĬ
    -0.20
    éĽĨåĽ¢èĤ¡ä»½
    -0.18
    æªĶ
    -0.18
    èĬ±å¼Ģ
    -0.18
    åī¯åİ¿éķ¿
    -0.18
    æĶ¯çº¿
    -0.18
    immer
    -0.18
    å¾ģ
    -0.18
    å±±åİ¿
    -0.17
    POSITIVE LOGITS
    erals
    0.21
    _gradients
    0.20
     Overs
    0.19
    éĶ¶
    0.19
    ity
    0.19
    åı¯æݧ
    0.18
    æĹłåģ¿
    0.18
    ite
    0.17
    ivil
    0.17
    示èĮĥ
    0.17
    Activations Density 0.010%

    No Known Activations