© 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. 1275
    Prev
    Next
    INDEX
    Explanations

    like a [noun]

    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
    éĥ¨åĪĨåĨħ容
    -0.27
    åŃĺéĩı
    -0.25
    æ´½
    -0.24
    éĥ¨åĪĨ
    -0.24
    æľīä¸Ģå®ļ
    -0.24
    çŃīåĨħ容
    -0.23
    åį³ä½¿æĺ¯
    -0.23
    ä¸įèĩ³äºİ
    -0.23
    åĴĮæľįåĬ¡
    -0.23
    odzi
    -0.23
    POSITIVE LOGITS
    ä¸Ģæł·
    0.27
    Moved
    0.24
    NSS
    0.24
    èĪ¬çļĦ
    0.23
    inals
    0.23
    essed
    0.23
    ä¸Ģ樣
    0.23
     unstoppable
    0.23
     spokes
    0.22
    /security
    0.22
    Activations Density 0.023%

    No Known Activations