© 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. 2823
    Prev
    Next
    INDEX
    Explanations

    integral part / component / figure / aspect

    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
    lands
    -0.24
    scape
    -0.23
    liness
    -0.22
    yer
    -0.21
    kel
    -0.20
    petition
    -0.20
    æ®ĥ
    -0.20
    anford
    -0.20
    serial
    -0.20
    rtl
    -0.20
    POSITIVE LOGITS
    ity
    0.36
    mente
    0.28
    izing
    0.26
    ç»ĦæĪIJéĥ¨åĪĨ
    0.25
    ities
    0.25
    ãģĵãģ¨
    0.24
    istic
    0.23
    /help
    0.22
     обÑĢазом
    0.22
    æĪIJåijĺ
    0.20
    Activations Density 0.013%

    No Known Activations