© 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. 1106
    Prev
    Next
    INDEX
    Explanations

    application, repository, television, Kingdom, States

    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
    &S
    -0.22
    亮çĤ¹
    -0.21
    ä¿©
    -0.21
    -API
    -0.21
    æŃ¥æŃ¥
    -0.21
    &W
    -0.20
    Anyone
    -0.20
    çħ
    -0.20
    äºĪ
    -0.20
    allo
    -0.20
    POSITIVE LOGITS
    swer
    0.24
     sir
    0.23
    è¿Ļ件äºĭæĥħ
    0.22
     ------>
    0.22
    иÑĪ
    0.21
    §è¡Į
    0.21
    isor
    0.20
    ugar
    0.20
    çľĭä¸Ģçľĭ
    0.20
    mov
    0.20
    Activations Density 0.927%

    No Known Activations