© 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. 74
    Prev
    Next
    INDEX
    Explanations

    crane

    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
    nya
    -0.23
    onds
    -0.21
    rd
    -0.21
    normal
    -0.21
    sWith
    -0.21
    seller
    -0.20
    ness
    -0.20
    éļ¾æĢª
    -0.20
    calar
    -0.20
    sdk
    -0.20
    POSITIVE LOGITS
    shaft
    0.23
    enberg
    0.23
    çĪ·
    0.21
    çĵ´
    0.19
    ights
    0.19
     móc
    0.19
    ãģĵãģ¨
    0.19
    ðŁı»
    0.18
     lift
    0.18
     cabo
    0.18
    Activations Density 0.013%

    No Known Activations