© 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. 541
    Prev
    Next
    INDEX
    Explanations

    elected officials or offices

    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
    ish
    -0.27
    aval
    -0.23
    æĢ§çĸ¾çĹħ
    -0.23
    oco
    -0.22
    heat
    -0.22
     enough
    -0.22
     upcoming
    -0.21
    roll
    -0.21
    wards
    -0.21
    likelihood
    -0.21
    POSITIVE LOGITS
    们éĥ½
    0.26
    们
    0.24
    tres
    0.24
    æľºæŀĦ
    0.24
     caliber
    0.24
     institutions
    0.23
    ANNEL
    0.23
    人士
    0.23
    ç»ĦæĪIJçļĦ
    0.22
    EW
    0.22
    Activations Density 0.010%

    No Known Activations