© 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. 2915
    Prev
    Next
    INDEX
    Explanations

    social account

    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
    fty
    -0.22
    **č↵
    -0.21
     _č↵
    -0.21
    opo
    -0.20
     Assumes
    -0.20
     SCRIPT
    -0.20
     |č↵
    -0.20
    Reject
    -0.19
    El
    -0.19
     ''č↵
    -0.19
    POSITIVE LOGITS
    adin
    0.23
    ↵ ↵
    0.21
     aforementioned
    0.20
    ä¸Ĭè¿°
    0.20
     above
    0.19
    sd
    0.19
    HLT
    0.19
    otron
    0.19
     again
    0.19
    simp
    0.19
    Activations Density 3.017%

    No Known Activations