© 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. 2461
    Prev
    Next
    INDEX
    Explanations

    May you

    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
    akin
    -0.27
    sek
    -0.25
    ite
    -0.25
    top
    -0.24
    è¦ģä¹Ī
    -0.23
    æ±´
    -0.23
     appendix
    -0.23
    tel
    -0.23
     Appendix
    -0.22
    äºĭåħĪ
    -0.22
    POSITIVE LOGITS
    UDA
    0.21
    è¿Ļä¸ĢåĪĩ
    0.21
    .INSTANCE
    0.21
    èĵij
    0.21
    FromString
    0.21
    _false
    0.21
    .rank
    0.21
    écoute
    0.21
     doubted
    0.21
    NOP
    0.20
    Activations Density 0.047%

    No Known Activations