© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2637
    Prev
    Next
    INDEX
    Explanations

    eyes

    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
     ÑįлекÑĤÑĢо
    -0.20
    åĮ»ç§ij大åѦ
    -0.19
    åı£å¤´
    -0.18
    æİĴ骨
    -0.18
    ä¼Ļ
    -0.18
    起身
    -0.17
    èįĩ
    -0.17
    æ°Ķæģ¯
    -0.17
    TEE
    -0.17
    nable
    -0.17
    POSITIVE LOGITS
    -catching
    0.33
    -eyed
    0.32
    ight
    0.32
    een
    0.28
    lessly
    0.26
    fulness
    0.25
    hood
    0.25
    prints
    0.24
    ning
    0.23
    gence
    0.23
    Activations Density 0.038%

    No Known Activations