© 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. 13726
    Prev
    Next
    INDEX
    Explanations

    night, island, blood, bulb

    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
     Savage
    -0.23
    æĺ¯ä¸Ģ家
    -0.19
    ä¸įéĻIJ
    -0.19
    .cz
    -0.19
    æĽ´æ·±
    -0.18
    inati
    -0.18
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.18
    æīĢåľ¨
    -0.18
    åįł
    -0.18
    åĬĽ
    -0.17
    POSITIVE LOGITS
    èĦ
    0.23
    PropertyName
    0.21
    å°¤åħ¶
    0.20
    -slide
    0.19
    APO
    0.19
    InstanceId
    0.19
    icularly
    0.18
    .colors
    0.18
    apat
    0.18
    尤为
    0.18
    Activations Density 0.201%

    No Known Activations