© 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. 12732
    Prev
    Next
    INDEX
    Explanations

    air conditioner, power, motor, amplifier

    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
    åıijèĤ²
    -0.23
     Vulcan
    -0.20
    产æĿĥ
    -0.20
    éĥģ
    -0.20
    æľĢæĹ©
    -0.20
    ä¹ĭç¾İ
    -0.19
    hin
    -0.19
     Bray
    -0.19
    çĸ¾
    -0.19
    uj
    -0.18
    POSITIVE LOGITS
    æ¯ı次
    0.26
    é«ĺæĺĤ
    0.26
    æ¯ı次éĥ½
    0.24
     overhead
    0.22
    ä¸įå¿ħè¦ģçļĦ
    0.21
    笺
    0.20
    _misc
    0.20
     activities
    0.20
    é¢ijç¹ģ
    0.19
    å¾ĺå¾Ĭ
    0.19
    Activations Density 0.045%

    No Known Activations