© 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. 2069
    Prev
    Next
    INDEX
    Explanations

    actual

    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
     participation
    -0.23
    .compress
    -0.23
     rivalry
    -0.23
    DateFormat
    -0.23
    æ¿Ģæ´»
    -0.23
    å°ģéĹŃ
    -0.23
    _compress
    -0.22
    æºIJæºIJ
    -0.22
    为æѤ
    -0.22
    KIT
    -0.22
    POSITIVE LOGITS
    å®ŀéĻħ
    0.62
    çļĦå®ŀéĻħ
    0.56
    actual
    0.55
     actual
    0.53
    Actual
    0.52
    實éļĽ
    0.50
    (actual
    0.49
     Actual
    0.49
    _actual
    0.46
    .actual
    0.45
    Activations Density 0.217%

    No Known Activations