© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 16514
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings

    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
    à¸Ħà¸ĵะà¸ģรรม
    -0.32
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.29
    à¸Ħะà¹ģà¸Ļ
    -0.26
    à¹Ĥà¸ļรา
    -0.26
    à¹Ģà¸īà¸ŀ
    -0.25
     มà¸ģร
    -0.24
    à¸ķำà¹ģ
    -0.24
    à¸Ļà¹Ĥย
    -0.23
    à¹Ģศรษ
    -0.23
     à¹Ģมษ
    -0.23
    POSITIVE LOGITS
    çĺª
    0.24
    俦
    0.22
    è¸ī
    0.20
    æ§ģ
    0.20
    åľ¨çݩ家ä¸Ń
    0.19
    èĶ«
    0.19
     wyÅĤÄħcznie
    0.19
    ous
    0.19
    åĺ¬
    0.19
    窸
    0.19
    Activations Density 0.226%

    No Known Activations