© 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. 2802
    Prev
    Next
    INDEX
    Explanations

    request for examples or details

    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
     remar
    -0.25
    追éĢIJ
    -0.22
    颤
    -0.21
    ais
    -0.21
    æĤłä¹ħ
    -0.21
     tint
    -0.21
     chú
    -0.21
    注æĦı
    -0.21
    istr
    -0.20
     Retrie
    -0.20
    POSITIVE LOGITS
    ä»ĭç»įä¸Ģä¸ĭ
    0.38
    详ç»Ĩ
    0.34
    åijĬè¯īæĪij
    0.33
    åĨĻåĩº
    0.32
    详ç»ĨçļĦ
    0.31
     please
    0.31
     clearer
    0.29
     details
    0.29
    æķĻãģĪãģ¦
    0.29
    ç»ĻæĪij
    0.28
    Activations Density 0.172%

    No Known Activations