© 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. 1760
    Prev
    Next
    INDEX
    Explanations

    names ending with d, san, ini, ana

    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
     aggressively
    -0.26
     serviced
    -0.24
     ZIP
    -0.24
     bluff
    -0.23
     bizarre
    -0.23
     IDX
    -0.22
     OMG
    -0.22
    íĿ¡
    -0.22
     #:
    -0.22
     flown
    -0.22
    POSITIVE LOGITS
    ÑĩÑĢежден
    0.29
     пÑĢиÑıÑĤн
    0.28
    æ®·
    0.28
    æĺĵäºİ
    0.26
    индив
    0.25
     поÑģколÑĮ
    0.24
    вÑĪиÑģ
    0.24
    å¯ĵ
    0.24
    çĶ«
    0.24
    åIJİæŀľ
    0.24
    Activations Density 0.152%

    No Known Activations