© 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. 1222
    Prev
    Next
    INDEX
    Explanations

    appearance vs identity

    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
    æĪIJå°±æĦŁ
    -0.25
    stroy
    -0.24
    -dom
    -0.23
    urs
    -0.23
     cel
    -0.22
    parsers
    -0.22
     prosecutions
    -0.21
    宣åijĬ
    -0.21
    æݢ索
    -0.21
    解åĨ³æĸ¹æ¡Ī
    -0.21
    POSITIVE LOGITS
    å¤ĸ表
    0.32
     naked
    0.30
    é¢ľåĢ¼
    0.28
     superficial
    0.28
    å¤ĸè§Ĥ
    0.27
    缸å¤Ħ
    0.26
    éķ¿çĽ¸
    0.26
    åħ¶æīĢ
    0.26
    ä¸Ģçľ¼
    0.25
    å¤ĸå½¢
    0.25
    Activations Density 0.026%

    No Known Activations