© 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. 15770
    Prev
    Next
    INDEX
    Explanations

    game titles like Fallout, Battlefield, Mega Man

    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
    æĺŃ
    -0.20
    è¡Įæĥħ
    -0.19
    为广大
    -0.19
    лов
    -0.18
    awa
    -0.18
    SIZE
    -0.18
    _scripts
    -0.18
    Declaration
    -0.18
    erot
    -0.18
     Ivory
    -0.17
    POSITIVE LOGITS
    å¼ĢæľĹ
    0.19
    ä¹IJè§Ĥ
    0.18
    çĽĺçĤ¹
    0.18
    åĽ½éĻħåIJĪä½ľ
    0.18
    å¼ĢèĬ±
    0.18
    è¿ĻæĶ¯
    0.18
     McGill
    0.18
    ois
    0.18
    æħ·æħ¨
    0.18
    çĴ§
    0.18
    Activations Density 0.001%

    No Known Activations