© 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. 2213
    Prev
    Next
    INDEX
    Explanations

    Prefixes of specific names and products

    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
    limitations
    -0.23
    ()._
    -0.23
     contempor
    -0.23
    .shtml
    -0.22
    æ²»çIJĨä½ĵç³»
    -0.22
     bureauc
    -0.22
    andbox
    -0.22
    ournals
    -0.22
    installer
    -0.22
    çļĦåIJĪä½ľ
    -0.22
    POSITIVE LOGITS
    ®
    0.27
     sight
    0.26
     standard
    0.24
     scent
    0.24
     color
    0.24
    -type
    0.24
     suction
    0.23
     type
    0.23
     drying
    0.23
     electroly
    0.23
    Activations Density 0.190%

    No Known Activations