© 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. 927
    Prev
    Next
    INDEX
    Explanations

    who know

    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
    fung
    -0.26
    峧
    -0.24
    otype
    -0.23
    length
    -0.22
    ATYPE
    -0.22
    æ¿Ģæ´»
    -0.22
    è¹¾
    -0.22
    æ¦ĥ
    -0.22
    ç½½
    -0.22
    _UNLOCK
    -0.21
    POSITIVE LOGITS
     who
    0.35
    çļĦ人æĿ¥è¯´
    0.32
     whom
    0.30
     themselves
    0.28
     quienes
    0.27
    æĺ¯è°ģ
    0.26
     genuinely
    0.25
    who
    0.25
     interviewed
    0.25
    åľŁåľ°
    0.24
    Activations Density 0.106%

    No Known Activations