© 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. 15958
    Prev
    Next
    INDEX
    Explanations

    discharge tube, printing material, encryption key, brake drum, hydraulic fluid

    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
     Kern
    -0.19
    ç¾İè§Ĥ
    -0.18
    sets
    -0.18
    Untitled
    -0.18
    ropdown
    -0.18
    asts
    -0.17
    asis
    -0.17
    zung
    -0.17
    rightness
    -0.17
    rob
    -0.17
    POSITIVE LOGITS
    èµĸ以
    0.26
    åīįãģ®
    0.25
    ä¸ĵçĶ¨
    0.25
     ingredients
    0.24
    -ready
    0.23
    æīĢéľĢçļĦ
    0.22
    æīĢéľĢè¦ģçļĦ
    0.22
    èij³
    0.21
    æĨĭ
    0.20
    æŶéĹ´åĴĮ
    0.20
    Activations Density 0.749%

    No Known Activations