© 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. 15360
    Prev
    Next
    INDEX
    Explanations

    Join us

    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
     dom
    -0.19
    (da
    -0.19
    éĥ½è¯´
    -0.19
    çļİ
    -0.19
    åĨ³ä¸į
    -0.18
    åĬŁè¯¾
    -0.18
    åĿıäºĨ
    -0.18
    ual
    -0.18
    çķĮçļĦ
    -0.17
     executive
    -0.17
    POSITIVE LOGITS
    çĿ£
    0.18
    èĤ¤
    0.18
    lyph
    0.18
    天èĬ±
    0.18
    ourg
    0.18
    严åİīæīĵåĩ»
    0.18
    itat
    0.17
    个人è§ĤçĤ¹
    0.17
    ably
    0.17
    èĦĤ
    0.17
    Activations Density 0.004%

    No Known Activations