© 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. 2775
    Prev
    Next
    INDEX
    Explanations

    publishers, databases, information providers

    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
     sacr
    -0.27
     crafts
    -0.26
    éĢłåŀĭ
    -0.26
     дÑĥÑħов
    -0.24
     idol
    -0.24
     bootloader
    -0.24
     Sacr
    -0.24
     selfish
    -0.23
     drained
    -0.23
     Hopefully
    -0.23
    POSITIVE LOGITS
     subscription
    0.43
    订éĺħ
    0.40
    å¹´æĬ¥
    0.38
     proprietary
    0.37
     databases
    0.37
    æķ°æį®åºĵ
    0.37
     subscriptions
    0.37
    ä»ĺè´¹
    0.37
     premium
    0.36
     database
    0.35
    Activations Density 0.049%

    No Known Activations