© 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. 1930
    Prev
    Next
    INDEX
    Explanations

    required, references, qualitative, method

    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
     crunch
    -0.25
     unh
    -0.24
    æijĬ
    -0.24
    象
    -0.23
    .Inner
    -0.23
    纽
    -0.23
    çĪ¬
    -0.22
     resp
    -0.22
     incoming
    -0.22
    çļĦå±ĢéĿ¢
    -0.22
    POSITIVE LOGITS
    çĶ¨éĢĶ
    0.26
     applic
    0.25
     saline
    0.24
    ä¾ĭå¤ĸ
    0.24
    éĿĪ
    0.23
    ä»ħä¾Ľ
    0.23
    ë¡Ģ
    0.23
    itten
    0.23
     veterin
    0.23
    urga
    0.23
    Activations Density 0.005%

    No Known Activations