© 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. 2386
    Prev
    Next
    INDEX
    Explanations

    polymers and chemical compounds

    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
     Borough
    -0.27
    梢
    -0.23
    èķ¹
    -0.23
    PNG
    -0.22
    TTY
    -0.22
     Colony
    -0.22
     Ticket
    -0.22
     XS
    -0.21
    PROFILE
    -0.21
    łģ
    -0.21
    POSITIVE LOGITS
    å¡Į
    0.28
     polyester
    0.28
     builders
    0.28
     synthesis
    0.26
    -transition
    0.25
     Keto
    0.25
    -building
    0.25
    builder
    0.25
    builders
    0.25
    adders
    0.24
    Activations Density 0.118%

    No Known Activations