© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2467
    Prev
    Next
    INDEX
    Explanations

    define, include, package

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    æ®ĩ
    -0.25
    _comm
    -0.23
    çļĦæĪIJ绩
    -0.22
     aus
    -0.22
    å¾Īä¸įéĶĻ
    -0.22
    æ²Ļ滩
    -0.22
     Maur
    -0.21
     Len
    -0.21
    ç½ijç«Ļ建设
    -0.21
    åĴļ
    -0.21
    POSITIVE LOGITS
    rang
    0.26
     gears
    0.26
    å¦ĤæŀľæĤ¨
    0.23
    inct
    0.22
    æ°Ķæ°Ľ
    0.22
    æĶ¶æ¬¾
    0.22
    -family
    0.22
    ç¿¥
    0.22
    -suite
    0.21
    Parms
    0.21
    Activations Density 0.001%

    No Known Activations