© 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. 1325
    Prev
    Next
    INDEX
    Explanations

    cuff or puff

    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
    cape
    -0.22
    IZE
    -0.20
    æīĭèĩĤ
    -0.18
    æŀ¹
    -0.18
    ORE
    -0.18
    apolis
    -0.18
    ATIC
    -0.18
    ignum
    -0.18
     Antar
    -0.18
    丰ç¡ķ
    -0.18
    POSITIVE LOGITS
    iest
    0.25
    ingly
    0.23
    nowled
    0.23
    chair
    0.23
    cloth
    0.22
    人家
    0.22
    atura
    0.22
    ings
    0.22
    æĸ°éĹ»è®°èĢħ
    0.21
    trap
    0.21
    Activations Density 0.006%

    No Known Activations