© 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. 12664
    Prev
    Next
    INDEX
    Explanations

    some + noun

    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
    æĬ»
    -0.19
    æĥķ
    -0.19
    Dll
    -0.19
     Catalyst
    -0.19
    è·¤
    -0.18
     многиÑħ
    -0.18
     odom
    -0.18
    ory
    -0.18
    å·¥ä½ľä½ľé£İ
    -0.18
    é«»
    -0.18
    POSITIVE LOGITS
    鼶ç¢İ
    0.22
    æĿ¥èĩª
    0.19
    lp
    0.19
    cant
    0.18
     assort
    0.18
    å¾ģæ±Ĥ
    0.18
    å¤ĸéĿ¢
    0.18
    iner
    0.18
    ç²¾åĬĽ
    0.18
    裸
    0.17
    Activations Density 0.033%

    No Known Activations