© 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. 1686
    Prev
    Next
    INDEX
    Explanations

    interobserver / intraobserver

    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
    cd
    -0.23
    Assets
    -0.22
    phabet
    -0.22
    çıIJ
    -0.22
    æľºåĬ¨
    -0.22
    IQ
    -0.21
    lah
    -0.21
    Chess
    -0.21
     welcome
    -0.21
     umb
    -0.21
    POSITIVE LOGITS
    çĭ¬èĩª
    0.36
     solo
    0.33
     solitary
    0.33
    çĭ¬
    0.32
    åįķçĭ¬
    0.31
     solitude
    0.30
     alone
    0.30
    åѤçĭ¬
    0.30
    -alone
    0.28
    çĭ¬ç«ĭ
    0.27
    Activations Density 0.366%

    No Known Activations