© 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. 2297
    Prev
    Next
    INDEX
    Explanations

    common stock, common pleas, standard output

    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
    edImage
    -0.25
    æĪIJè´¥
    -0.24
    ivia
    -0.24
    setSize
    -0.24
     arcs
    -0.23
     extrad
    -0.23
     junk
    -0.23
     congress
    -0.23
    iven
    -0.22
     ASAP
    -0.22
    POSITIVE LOGITS
     subsidiary
    0.24
    åĭĩæ°Ķ
    0.22
     Investor
    0.22
     sede
    0.22
     investors
    0.22
    飧æĢ§
    0.22
     Essex
    0.21
     Deferred
    0.21
    /epl
    0.21
     Provision
    0.21
    Activations Density 0.004%

    No Known Activations