© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 987
    Prev
    Next
    INDEX
    Explanations

    Dixieland Jass Band, pro-resolving, teno, Metrewave, Moher, Benedict Society, Goon Squad

    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
    CTYPE
    -0.23
    ABI
    -0.23
    Thumb
    -0.23
    oke
    -0.23
     PROVIDED
    -0.22
    IFDEF
    -0.22
    efault
    -0.22
    iping
    -0.22
    AB
    -0.22
    ATEST
    -0.21
    POSITIVE LOGITS
    ç±į
    0.27
    åıijçĶŁåľ¨
    0.25
    æĦıä¹īä¸ĬçļĦ
    0.25
     Z
    0.24
    (er
    0.23
    åºĶçĶ¨äºİ
    0.23
     Julius
    0.23
    ä¸ĢæŃ¥æŃ¥
    0.23
     Ri
    0.22
    æīĭæ³ķ
    0.22
    Activations Density 0.174%

    No Known Activations