© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 6
    Prev
    Next
    INDEX
    Explanations

    fictional character detail

    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
    æĵįä½ľ
    -0.27
    iya
    -0.25
    INA
    -0.24
    梯
    -0.24
     moveTo
    -0.24
    çļĦæĵįä½ľ
    -0.23
    ĵįä½ľ
    -0.23
    æĭ¥æĬ±
    -0.23
     boyc
    -0.23
    unlink
    -0.22
    POSITIVE LOGITS
     flesh
    0.39
     fictional
    0.39
     backstory
    0.36
    èĻļæŀĦ
    0.35
    åĪĽä½ľ
    0.35
     detail
    0.34
     characters
    0.34
    ç¼ľ
    0.33
     fict
    0.32
    设å®ļ
    0.32
    Activations Density 0.060%

    No Known Activations