© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 110
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    æĻĤåĢĻ
    -0.27
     gere
    -0.23
    笳
    -0.23
    åı·çº¿
    -0.22
    	TokenName
    -0.22
    CHED
    -0.21
    qli
    -0.21
    帳
    -0.20
    æĢ¯
    -0.20
    éķľå¤´
    -0.20
    POSITIVE LOGITS
    æijĺ
    0.26
     Darling
    0.24
    .ensure
    0.23
    [url
    0.21
     Cousins
    0.21
    è¤
    0.21
     Sprint
    0.21
     sprint
    0.21
    вÑıз
    0.20
    /functions
    0.20
    Activations Density 0.006%

    No Known Activations