© 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. 2095
    Prev
    Next
    INDEX
    Explanations

    numbers and code

    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
    ffective
    -0.23
    ighted
    -0.22
    arsi
    -0.21
    cult
    -0.21
    Exclusive
    -0.20
     SSA
    -0.20
    _patterns
    -0.20
    xcd
    -0.20
    |[
    -0.20
    iams
    -0.20
    POSITIVE LOGITS
    人æ°ijåĮ»éĻ¢
    0.24
    {}.
    0.23
    åĴĮåľ°åĮº
    0.23
    æŁĴ
    0.21
    èĩªå¸¦
    0.21
    ioxide
    0.21
    ä¸ĭ称
    0.20
    大åħ¨
    0.20
    éĵ®
    0.20
     Vir
    0.19
    Activations Density 0.147%

    No Known Activations