© 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. 15087
    Prev
    Next
    INDEX
    Explanations

    N/A, Not available, undefined, not set

    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
    itize
    -0.21
    eries
    -0.20
    æ°¸è¿ľ
    -0.20
    天ä¸ĭ
    -0.19
    nap
    -0.19
    æ°¸
    -0.19
    åĮĹ
    -0.18
    emode
    -0.18
     streak
    -0.18
    ä»İæľª
    -0.18
    POSITIVE LOGITS
    èĥ«
    0.21
    ä»ĸå¦Ī
    0.20
    çī¹åĪ«å£°æĺİ
    0.20
    бл
    0.19
    缬
    0.18
    igation
    0.18
    æķijæĬ¤
    0.18
    çĥ¦èºģ
    0.17
    åī²
    0.17
    æĸ¼æĺ¯
    0.17
    Activations Density 0.036%

    No Known Activations