© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 505
    Prev
    Next
    INDEX
    Explanations

    acid, sulfate, dioxide, molecules

    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
     scene
    -0.28
     jur
    -0.27
     scenes
    -0.27
    owner
    -0.27
     Owner
    -0.26
     stamp
    -0.26
     owner
    -0.26
     premises
    -0.25
     chiến
    -0.25
     offices
    -0.25
    POSITIVE LOGITS
    -containing
    0.47
    åIJ«éĩı
    0.39
    aceous
    0.38
     dioxide
    0.36
    -rich
    0.35
     molecules
    0.35
     soluble
    0.34
     sulfate
    0.34
    áĢĵ
    0.33
     deficiency
    0.32
    Activations Density 2.080%

    No Known Activations