© 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. 819
    Prev
    Next
    INDEX
    Explanations

    design concepts and structures

    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
    èģĮå·¥
    -0.25
     consumption
    -0.24
    åijĺå·¥
    -0.24
    æĬ¥éĶĢ
    -0.24
     employee
    -0.23
    æĬµ
    -0.23
     getService
    -0.23
    Launcher
    -0.23
    hp
    -0.22
    åĨĴ
    -0.22
    POSITIVE LOGITS
    ç¾İåѦ
    0.44
    æĬĢæ³ķ
    0.44
    å¸ĥå±Ģ
    0.43
    æŀĦæĢĿ
    0.42
    èīºæľ¯
    0.40
    审ç¾İ
    0.40
    åŁºæľ¬åİŁåĪĻ
    0.40
    ç»ĺçĶ»
    0.39
     aesthetics
    0.39
    åĽ¾æ¡Ī
    0.39
    Activations Density 0.052%

    No Known Activations