© 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. 1939
    Prev
    Next
    INDEX
    Explanations

    standard, champion, -era

    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
    olk
    -0.26
    vtk
    -0.24
    lint
    -0.23
    oke
    -0.23
    åªĴä½ĵæĬ¥éģĵ
    -0.23
    intValue
    -0.22
    èĪĨ
    -0.22
    èľĥ
    -0.22
    £
    -0.22
    boat
    -0.22
    POSITIVE LOGITS
     standard
    0.28
    æłĩåĩĨ
    0.28
    standard
    0.26
     champion
    0.26
     champions
    0.24
    -era
    0.24
    çī©
    0.23
    -standard
    0.23
     supers
    0.22
    еÑĪÑĮ
    0.22
    Activations Density 0.014%

    No Known Activations