© 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. 1104
    Prev
    Next
    INDEX
    Explanations

    aimed at a target audience

    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
    转åĬ¨
    -0.27
     procedures
    -0.26
     Procedures
    -0.24
    åħijçİ°
    -0.24
    对åŃ©åŃIJ
    -0.23
    溯æºIJ
    -0.23
    procedure
    -0.23
    OfDay
    -0.22
    缸继
    -0.22
    ENSOR
    -0.22
    POSITIVE LOGITS
    åıĹä¼Ĺ
    0.59
     audiences
    0.58
    人群
    0.55
     audience
    0.53
     Audience
    0.39
     clientele
    0.39
    人群ä¸Ń
    0.39
    群ä½ĵ
    0.37
    è§Ĥä¼Ĺ
    0.37
    -target
    0.35
    Activations Density 0.121%

    No Known Activations