© 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. 1349
    Prev
    Next
    INDEX
    Explanations

    identifying numbers and IDs

    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
    åĬ©éķ¿
    -0.24
    ISA
    -0.24
    åIJĥè¿ĩ
    -0.24
    OfSize
    -0.23
    åij¨æľ«
    -0.23
    æĮĩ示
    -0.23
    æ´Ĺ
    -0.23
    ä¸ĢæŶ
    -0.22
    STEM
    -0.21
    .Handled
    -0.21
    POSITIVE LOGITS
    ember
    0.27
    smith
    0.26
    mine
    0.24
    keh
    0.24
     profile
    0.24
    haar
    0.24
    _my
    0.24
    @test
    0.24
    id
    0.23
     alumni
    0.23
    Activations Density 0.079%

    No Known Activations