© 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. 1749
    Prev
    Next
    INDEX
    Explanations

    Patrick followed by names

    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
    OrUpdate
    -0.21
    cter
    -0.20
    verts
    -0.19
    éŀħ
    -0.19
    enu
    -0.19
    ä½ľåĿĬ
    -0.19
    èĥĦ
    -0.19
    ining
    -0.18
    ction
    -0.18
    ocop
    -0.18
    POSITIVE LOGITS
    ian
    0.23
     minded
    0.23
    ville
    0.23
    son
    0.20
    ss
    0.20
    imoto
    0.20
    furt
    0.20
    ity
    0.19
    pole
    0.19
    opol
    0.19
    Activations Density 0.004%

    No Known Activations