© 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. 2090
    Prev
    Next
    INDEX
    Explanations

    undertake actions or initiatives

    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
    ÑĮÑĤе
    -0.20
    pell
    -0.20
    oted
    -0.19
     apartments
    -0.19
    éĵĽ
    -0.18
    /buttons
    -0.18
    akk
    -0.18
    atura
    -0.18
    確
    -0.18
    rete
    -0.18
    POSITIVE LOGITS
     undertaken
    0.23
    äºĨä¸Ģç³»åĪĹ
    0.22
    æѤäºĭ
    0.21
    ä¸ºæľŁ
    0.21
     endeavors
    0.21
    cka
    0.21
    èī°å·¨
    0.20
    aurus
    0.20
     поиÑģк
    0.20
    ors
    0.20
    Activations Density 0.008%

    No Known Activations