© 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. 11122
    Prev
    Next
    INDEX
    Explanations

    National Register of Historic Places

    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
    _customize
    -0.19
    eya
    -0.18
    ç½ijç«Ļåľ°åĽ¾
    -0.18
    åľŁèĢ³åħ¶
    -0.18
    ender
    -0.18
    osto
    -0.18
     Conf
    -0.18
    éĴ»çŁ³
    -0.18
    nesia
    -0.17
     khá»ķ
    -0.17
    POSITIVE LOGITS
    ä¸įå¿į
    0.27
    建çŃij
    0.25
     пÑĢиÑıÑĤн
    0.22
    æĦıè§ģåıįé¦Ī
    0.21
    åħ¸åŀĭçļĦ
    0.21
    樾
    0.21
    楼å®ĩ
    0.21
    楼
    0.20
    建çŃij设计
    0.20
    建çŃijéĿ¢ç§¯
    0.20
    Activations Density 0.055%

    No Known Activations