© 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. 680
    Prev
    Next
    INDEX
    Explanations

    unique features or ability

    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
    ãģıãĤĮ
    -0.22
    ண
    -0.21
    æľĪ亮
    -0.20
     gÅĤów
    -0.19
    Unnamed
    -0.19
    iday
    -0.18
    /her
    -0.18
    éĺŁä¼į建设
    -0.18
    acular
    -0.18
    anger
    -0.18
    POSITIVE LOGITS
    ities
    0.33
    idades
    0.27
    ä¹ĭå¤Ħ
    0.27
    æĢ§åĴĮ
    0.26
    ITIES
    0.26
    对å¾ħ
    0.25
    åľ¨äºİ
    0.25
     insights
    0.25
    å°±åľ¨äºİ
    0.24
    asa
    0.24
    Activations Density 0.034%

    No Known Activations