© 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. 15792
    Prev
    Next
    INDEX
    Explanations

    sharing agreement

    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
    EDI
    -0.22
    _RAD
    -0.19
    åİ©
    -0.19
    _ped
    -0.18
    è¾ĵäºĨ
    -0.18
    åĴĮ个人
    -0.18
    衽
    -0.18
    ç½Ĺæĸ¯
    -0.18
    SAN
    -0.18
    åıijè¾¾
    -0.18
    POSITIVE LOGITS
     alike
    0.25
     equally
    0.21
    ä¸Ģæł·
    0.20
    acon
    0.19
    èıĩ
    0.19
    å¿Ļç¢Į
    0.19
    asca
    0.18
    æ´Ļ
    0.18
    åħĭåĪ¶
    0.18
    è´¢æĶ¿éĥ¨
    0.18
    Activations Density 0.046%

    No Known Activations