© 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. 686
    Prev
    Next
    INDEX
    Explanations

    job titles and affiliations

    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
    pter
    -0.26
    ima
    -0.26
    ys
    -0.24
    nen
    -0.23
    inals
    -0.23
    æIJĶ
    -0.23
    oor
    -0.22
    çŃīä¸Ģæī¹
    -0.22
    elden
    -0.22
    vere
    -0.21
    POSITIVE LOGITS
     Tail
    0.27
     Emer
    0.27
    åħ¼
    0.24
     Consultant
    0.23
     Consulting
    0.23
    (cv
    0.23
     Member
    0.23
     unterstützt
    0.23
     Chief
    0.22
     Representative
    0.22
    Activations Density 0.082%

    No Known Activations