© 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. 2985
    Prev
    Next
    INDEX
    Explanations

    hair, barber, site, Pok

    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
    åħ³èģĶ
    -0.24
     hailed
    -0.24
    аÑĨи
    -0.24
     cred
    -0.24
    è¿ĻäºĽä¸ľè¥¿
    -0.23
     ìļ´ìĺģ
    -0.23
    ä¸ĸçķĮä¸Ĭ
    -0.23
    elib
    -0.23
    污
    -0.23
    TODO
    -0.23
    POSITIVE LOGITS
    bih
    0.26
    bai
    0.26
    arching
    0.25
    æīĭæİĮ
    0.25
     evenly
    0.25
     randomized
    0.25
    .unshift
    0.25
    lettes
    0.25
    è½»è½»åľ°
    0.24
    /front
    0.24
    Activations Density 0.006%

    No Known Activations