© 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. 11558
    Prev
    Next
    INDEX
    Explanations

    me followed by question words

    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
    åIJģ
    -0.24
    egov
    -0.23
    éĤĢ请
    -0.19
     Eis
    -0.19
    IXEL
    -0.19
    ILLE
    -0.18
    èĥŀ
    -0.18
    ERVE
    -0.18
     Gór
    -0.18
    /li
    -0.18
    POSITIVE LOGITS
    ä¸Ģè§Ī
    0.22
     scarc
    0.21
    羣缸
    0.20
    æĮĩçĤ¹
    0.19
    ÑıÑħ
    0.18
    ç®Ģ
    0.17
     ÑĢезÑĥлÑĮÑĤаÑĤ
    0.17
    èĬ±å¼Ģ
    0.17
    çĥ¦èºģ
    0.17
    SET
    0.17
    Activations Density 0.033%

    No Known Activations