© 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. 12836
    Prev
    Next
    INDEX
    Explanations

    permanent installed

    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
    æľīåIJį
    -0.20
    å½±
    -0.19
     free
    -0.19
    æIJŀ
    -0.19
    æħ¢
    -0.18
    人为
    -0.18
    èĽŁ
    -0.18
    è§ĤæľĽ
    -0.18
    æ³·
    -0.18
    çĦ¦çĤ¹
    -0.18
    POSITIVE LOGITS
    èŀįåħ¥
    0.30
    æ°¸ä¹ħ
    0.30
     permanent
    0.29
     perman
    0.29
    permanent
    0.28
    ä¸Ģä½ĵ
    0.28
    ä¸Ģä½ĵåĮĸ
    0.28
    æ·±å±Ĥ
    0.26
    èŀį为ä¸Ģä½ĵ
    0.25
    èĢĮéĿŀ
    0.25
    Activations Density 0.276%

    No Known Activations