© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 395
    Prev
    Next
    INDEX
    Explanations

    persons with

    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
    çļĦæŶéĹ´éĩĮ
    -0.23
    ipse
    -0.23
    ting
    -0.23
    ture
    -0.23
    heet
    -0.23
    tparam
    -0.22
    ĤŃ
    -0.21
    imate
    -0.20
    fter
    -0.20
    istrate
    -0.20
    POSITIVE LOGITS
    hood
    0.25
    å½¹
    0.22
    /people
    0.22
    çļĨ
    0.22
     hor
    0.22
    m
    0.21
    ervice
    0.20
    chaft
    0.20
    r
    0.20
     interested
    0.20
    Activations Density 0.011%

    No Known Activations