© 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. 2106
    Prev
    Next
    INDEX
    Explanations

    ovarian stimulation, syndrome, follicle, disease

    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
    Sink
    -0.26
     honor
    -0.25
     footwear
    -0.24
     toilets
    -0.24
    æĬ¤æłı
    -0.23
    аÑģ
    -0.23
    æ¸ĹéĢı
    -0.22
     cuisine
    -0.22
     leve
    -0.22
     keyst
    -0.22
    POSITIVE LOGITS
    åįµå·¢
    0.27
    _SCHED
    0.25
     ovarian
    0.25
    æķ°çĽ®
    0.24
    enu
    0.24
     follic
    0.24
    .scheduler
    0.23
    chedule
    0.23
    äºĮèĥİ
    0.23
     hormone
    0.23
    Activations Density 0.052%

    No Known Activations