© 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. 2696
    Prev
    Next
    INDEX
    Explanations

    viewpoints and perspective

    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
    åĬ¨ä½ľ
    -0.26
    室
    -0.25
    æ¯ĶèµĽä¸Ń
    -0.24
    å¹²ä»Ģä¹Ī
    -0.23
    contro
    -0.23
     Curl
    -0.22
    legg
    -0.22
    æ¶Ī
    -0.22
    abbreviation
    -0.21
    æ°´ä¸Ĭ
    -0.21
    POSITIVE LOGITS
    è§Ĩè§Ĵ
    0.72
     perspective
    0.65
     perspectives
    0.62
     Perspective
    0.50
     viewpoints
    0.50
     viewpoint
    0.48
    è§Ĵ度
    0.48
    çļĦè§Ĵ度
    0.45
     view
    0.44
    审è§Ĩ
    0.44
    Activations Density 0.082%

    No Known Activations