© 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. 13258
    Prev
    Next
    INDEX
    Explanations

    code formatting and special characters

    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
     Hess
    -0.20
    OTP
    -0.20
    æĬĢæľ¯æľįåĬ¡
    -0.20
    aviest
    -0.19
    íĴĭ
    -0.19
    dv
    -0.18
    eea
    -0.18
    asn
    -0.18
    è¸ı
    -0.18
    ALK
    -0.18
    POSITIVE LOGITS
    çļĦä¾ĭåŃIJ
    0.23
    æŁIJ
    0.22
    常è§ģçļĦ
    0.21
    红楼梦
    0.21
    ä¸ŃéĢĶ
    0.20
     insensitive
    0.20
    èµĸ
    0.20
    _cases
    0.20
    ç§
    0.20
    çĶļèĩ³
    0.20
    Activations Density 0.457%

    No Known Activations