© 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. 2188
    Prev
    Next
    INDEX
    Explanations

    doctors

    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
    tle
    -0.22
    çĥ¬
    -0.21
    éĩijèī²
    -0.21
    older
    -0.20
     Ñģобой
    -0.19
    交éĢļå·¥åħ·
    -0.19
    orem
    -0.18
    Į
    -0.18
    èī²
    -0.18
    rl
    -0.18
    POSITIVE LOGITS
    liness
    0.27
    ×ķת
    0.25
    ele
    0.23
    stown
    0.23
    ifice
    0.22
    ette
    0.21
    eurs
    0.21
    itat
    0.20
    è¿Ļ个èģĮä¸ļ
    0.20
    uments
    0.20
    Activations Density 0.010%

    No Known Activations