© 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. 14586
    Prev
    Next
    INDEX
    Explanations

    pipeline companies

    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
    æĦŁ
    -0.20
    åĸĩ
    -0.20
    udes
    -0.20
    æĵĴ
    -0.20
    éĤ£ä½į
    -0.19
     Leather
    -0.19
    aces
    -0.19
    è®Ń
    -0.19
    remarks
    -0.19
    _collision
    -0.18
    POSITIVE LOGITS
    åħ¬åı¸å°Ĩ
    0.24
    åħ¬åı¸çļĦ
    0.24
    è´¢
    0.21
    åħ¬åı¸åľ¨
    0.20
    æıIJåĩºçļĦ
    0.20
    æĹĹä¸ĭçļĦ
    0.19
    æĮģæľīçļĦ
    0.19
    Ī
    0.19
    æĹ¶ä»£çļĦ
    0.19
    æĶ¶è´Ń
    0.19
    Activations Density 0.026%

    No Known Activations