© 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. 1495
    Prev
    Next
    INDEX
    Explanations

    in vitro

    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
     Brewer
    -0.23
     Engl
    -0.23
     nickname
    -0.23
    转弯
    -0.23
     deprecated
    -0.22
     bastard
    -0.22
    UNG
    -0.21
    EMENT
    -0.20
     Camel
    -0.20
     line
    -0.20
    POSITIVE LOGITS
    æĿ¡ä»¶ä¸ĭ
    0.28
    åįķçĭ¬
    0.26
    æĿ¡ä»¶
    0.25
    çݯå¢ĥä¸ĭ
    0.24
    éĩįçİ°
    0.24
    ally
    0.23
    çݯå¢ĥä¸Ń
    0.23
    -alone
    0.23
    /place
    0.22
    isol
    0.22
    Activations Density 0.126%

    No Known Activations