© 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. 791
    Prev
    Next
    INDEX
    Explanations

    improper integral or continuous

    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
    æĸ°éĹ»ç½ij
    -0.23
    zet
    -0.23
    antan
    -0.22
     inkl
    -0.22
    -Oct
    -0.21
    éĹ°
    -0.21
    æģIJæĥ§
    -0.21
    -many
    -0.21
    ienne
    -0.21
    åĨĮ
    -0.21
    POSITIVE LOGITS
     restitution
    0.29
     aggravated
    0.25
    _requires
    0.25
    utt
    0.23
    ä½įæĸ¼
    0.22
    è·¯è¿ĩ
    0.22
     resulting
    0.22
    .backward
    0.22
    æģĤ
    0.22
     Pars
    0.21
    Activations Density 0.002%

    No Known Activations