© 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. 2286
    Prev
    Next
    INDEX
    Explanations

    behind positions

    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
    éħ¿
    -0.26
    çĹĩ
    -0.25
    æĨĶ
    -0.24
    éĶ°
    -0.23
    çĶŁäºİ
    -0.23
    æľªæĿ¥
    -0.23
    èĵĵ
    -0.23
    воÑĢ
    -0.23
    æŀ°
    -0.23
    tone
    -0.23
    POSITIVE LOGITS
    /front
    0.26
     behind
    0.26
    neath
    0.25
     gr
    0.24
     ech
    0.23
     Behind
    0.23
    /back
    0.22
    çľĭä¸įè§ģ
    0.22
     invisible
    0.21
    -facing
    0.21
    Activations Density 0.019%

    No Known Activations