© 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. 1919
    Prev
    Next
    INDEX
    Explanations

    contraception and Jenner

    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
    æĶ¾è¿Ľ
    -0.25
     Moody
    -0.23
     ALPHA
    -0.23
    dre
    -0.23
    åĤ»
    -0.22
    æ¥Ķ
    -0.22
    äºļ马
    -0.22
    ä¸ĭä¸Ģç¯ĩ
    -0.22
    fully
    -0.22
    ä½ľæģ¯
    -0.22
    POSITIVE LOGITS
    oscope
    0.29
    etro
    0.25
    oon
    0.25
    ató
    0.23
    yb
    0.22
    åŁĭ
    0.22
     Concat
    0.22
    oom
    0.22
    retval
    0.21
    chos
    0.21
    Activations Density 0.006%

    No Known Activations