© 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. 15593
    Prev
    Next
    INDEX
    Explanations

    just + recent action

    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
    ä¸į让
    -0.20
    éĤ£äºĽ
    -0.20
    ering
    -0.19
    åħ¶ä»ĸ人
    -0.19
    .pref
    -0.19
     others
    -0.18
    ä¸įå¼Ģ
    -0.18
    Neill
    -0.18
    ç¼ĺ
    -0.18
    зÑĥ
    -0.18
    POSITIVE LOGITS
    åıijå¸ĥçļĦ
    0.21
    æīįåıijçİ°
    0.20
    æĭ¨
    0.20
    new
    0.19
    宣å¸ĥ
    0.19
    åĨĴåĩº
    0.18
    æĪĸå°Ĩ
    0.18
    /current
    0.18
    hit
    0.18
    åıijçİ°
    0.17
    Activations Density 0.025%

    No Known Activations