© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3384
    Prev
    Next
    INDEX
    Explanations

    unknown / ship

    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
    Negative Logits
    MLS
    -0.25
     kInstruction
    -0.24
     Belgi
    -0.23
    .VK
    -0.23
    _TypeInfo
    -0.23
    REEN
    -0.23
    _marshall
    -0.23
     getClass
    -0.23
    -lnd
    -0.23
    Suppress
    -0.23
    POSITIVE LOGITS
     Unknown
    0.29
    unknown
    0.28
     unidentified
    0.28
    ship
    0.27
     N
    0.26
    slash
    0.26
    ships
    0.25
     unknown
    0.25
    inters
    0.25
     H
    0.25
    Activations Density 0.068%

    No Known Activations