© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15382
    Prev
    Next
    INDEX
    Explanations

    speaking up or out

    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
    ä¸Ģè¶Ł
    -0.18
    çķĻç»Ļ
    -0.18
    à¸ģารà¹ģสà¸Ķà¸ĩ
    -0.17
    éĦļ
    -0.17
    uria
    -0.17
     Pulitzer
    -0.17
    åľ¨ä¸Ģèµ·
    -0.17
    ability
    -0.17
    æıIJä¾ĽåķĨ
    -0.17
    å®īæİĴ
    -0.16
    POSITIVE LOGITS
    æĦıè§ģ
    0.22
     opinions
    0.20
    çĶ«
    0.19
    exter
    0.19
     WHETHER
    0.18
     Äijỡ
    0.18
    åħ³äºİ
    0.18
     пÑĢизна
    0.18
    emax
    0.17
     بش
    0.17
    Activations Density 0.012%

    No Known Activations