© 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. 2683
    Prev
    Next
    INDEX
    Explanations

    delimiters and following words

    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
    --)č↵
    -0.24
    åĥ»
    -0.23
    'gc
    -0.23
    .'</
    -0.23
    UTO
    -0.23
    éĴı
    -0.22
    %"><
    -0.22
    AccessType
    -0.22
    å®ļ
    -0.22
     Horde
    -0.21
    POSITIVE LOGITS
    :
    0.45
    ï¼ļ
    0.40
    :↵
    0.35
    :,
    0.35
    ï¼ļ↵
    0.31
    ä»Ģä¹Īåij¢
    0.30
    /on
    0.29
    :↵↵
    0.27
    /by
    0.27
    /platform
    0.27
    Activations Density 0.401%

    No Known Activations