© 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. 321
    Prev
    Next
    INDEX
    Explanations

    tr or org prefixes

    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
    uja
    -0.27
     lurking
    -0.27
    å±Ģ
    -0.23
    è¿«
    -0.23
     consum
    -0.22
    åIJĪä½ľ
    -0.22
    åķĨ
    -0.21
     depart
    -0.21
     recurs
    -0.21
    иÑĤелÑı
    -0.21
    POSITIVE LOGITS
    egend
    0.26
    eut
    0.23
    ield
    0.23
    Ţ
    0.22
    人æ°ijéĵ¶è¡Į
    0.21
    åģĮ
    0.21
     Battlefield
    0.21
    eft
    0.21
    WG
    0.21
    âĦ®
    0.21
    Activations Density 0.193%

    No Known Activations