© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1052
    Prev
    Next
    INDEX
    Explanations

    court of appeals cases

    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
    æŁ¬
    -0.24
    edb
    -0.23
    ality
    -0.22
    éĺħ读åħ¨æĸĩ
    -0.21
     BELOW
    -0.21
     Below
    -0.21
     hinter
    -0.21
    usters
    -0.21
    æľī两ç§į
    -0.21
    =-=-=-=-=-=-=-=-
    -0.20
    POSITIVE LOGITS
    wald
    0.28
    hea
    0.24
    宽æĿ¾
    0.23
     Narc
    0.22
    posable
    0.22
    æĸ°éĹ»
    0.21
    åģļ大åģļ强
    0.21
    éĶĢæ¯ģ
    0.21
    oke
    0.21
    bone
    0.21
    Activations Density 0.001%

    No Known Activations