© 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. 64
    Prev
    Next
    INDEX
    Explanations

    embolization, amalgams, intention, Cornell

    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
    NING
    -0.24
    tl
    -0.24
    vid
    -0.23
    YZ
    -0.21
    resher
    -0.21
    cloth
    -0.21
    DEV
    -0.21
    éĶĢ
    -0.21
    æ²IJæµ´
    -0.21
    pan
    -0.21
    POSITIVE LOGITS
    chedules
    0.27
    è¹Ļ
    0.23
    è´·
    0.23
    çĸ¤
    0.23
    ç¢
    0.23
    èĬĤå¥ı
    0.23
    uder
    0.22
    irma
    0.22
    apy
    0.22
    订è´Ń
    0.22
    Activations Density 0.002%

    No Known Activations