© 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. 12735
    Prev
    Next
    INDEX
    Explanations

    dialing telephone calls

    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
    bate
    -0.21
    æ±īæĹı
    -0.19
    iest
    -0.19
    eland
    -0.19
     Celebration
    -0.18
    åįĥå¹´
    -0.18
    ç¢Ĺ
    -0.17
    ulu
    -0.17
     milan
    -0.17
    ä¸įæľį
    -0.17
    POSITIVE LOGITS
     оÑĤкÑĢÑĭÑĤ
    0.23
    ä¼ł
    0.22
     пÑĢаво
    0.21
    лага
    0.20
    çĨĦ
    0.19
    ä¸ĢéĶ®
    0.19
    звон
    0.19
     SWITCH
    0.18
    åįģåĪĨéĴŁ
    0.18
    äºĶåĪĨéĴŁ
    0.18
    Activations Density 0.026%

    No Known Activations