© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 191
    Prev
    Next
    INDEX
    Explanations

    certifications and accreditations

    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
    设æĥ³
    -0.30
     ornament
    -0.26
    UNCH
    -0.26
    ç»ĵæŀĦè°ĥæķ´
    -0.26
    upert
    -0.26
    .decor
    -0.26
     extravag
    -0.26
    Decoration
    -0.26
     radical
    -0.25
     richness
    -0.25
    POSITIVE LOGITS
    èĢĥçĤ¹
    0.40
    åIJĪæł¼
    0.39
     accredited
    0.38
    è¾¾æłĩ
    0.38
    åıĸè¯ģ
    0.37
     certified
    0.36
     Approved
    0.35
     compliant
    0.35
    åŁ¹è®Ń
    0.35
     compliance
    0.35
    Activations Density 0.027%

    No Known Activations