© 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. 642
    Prev
    Next
    INDEX
    Explanations

    private message

    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
    ãģĵãģ¨
    -0.30
    ed
    -0.21
    ../
    -0.21
    /or
    -0.20
    rede
    -0.20
    cco
    -0.20
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.19
    STER
    -0.19
    uate
    -0.19
    shire
    -0.19
    POSITIVE LOGITS
    ships
    0.26
    urations
    0.20
    sWith
    0.20
    们éĥ½
    0.20
    /html
    0.19
     tắt
    0.19
    iami
    0.19
    atrix
    0.19
    ities
    0.18
    itarian
    0.18
    Activations Density 0.015%

    No Known Activations