© 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. 15771
    Prev
    Next
    INDEX
    Explanations

    online forum discussions

    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
    ONA
    -0.18
    Wonder
    -0.18
    ureau
    -0.17
    塵
    -0.17
    classpath
    -0.16
     Ryan
    -0.16
    igit
    -0.16
    lander
    -0.16
    rastructure
    -0.16
    rys
    -0.16
    POSITIVE LOGITS
    ä¹ĭæĺŁ
    0.22
    chine
    0.21
    ä¸Ģçĵ¶
    0.20
    аÑĨион
    0.19
    ä¸Ńèį¯
    0.19
    ä¸Ģç¢Ĺ
    0.18
    æ¸ħéĨĴ
    0.18
    åħ±è¯Ĩ
    0.18
    æijĪ
    0.18
    éĹ´éļĻ
    0.18
    Activations Density 0.007%

    No Known Activations