© 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. 16744
    Prev
    Next
    INDEX
    Explanations

    company or property funds

    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
    hum
    -0.21
    çĶŁæĦı
    -0.19
    çĥŃè¡Ģ
    -0.19
    Registers
    -0.19
     bearing
    -0.18
    Localization
    -0.18
    Newton
    -0.18
    å¼ºåĽ½
    -0.18
    appearance
    -0.18
    aled
    -0.18
    POSITIVE LOGITS
    åIJĮç±»
    0.23
    è£ħéħįå¼ı
    0.22
    èµĦ产管çIJĨ
    0.22
    illow
    0.22
    åŃ£èĬĤ
    0.21
    èĩªæľī
    0.21
    åħ¨èµĦ
    0.21
    èµĦ产
    0.21
    æīĺ管
    0.20
    æĢ»èµĦ产
    0.20
    Activations Density 0.056%

    No Known Activations