© 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. 2193
    Prev
    Next
    INDEX
    Explanations

    educational, research, and entertainment purposes

    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
     Stem
    -0.23
    ÑĤен
    -0.23
    stem
    -0.23
    jee
    -0.23
     займ
    -0.22
     witness
    -0.21
     Policies
    -0.21
    JD
    -0.21
    -neck
    -0.21
     policies
    -0.21
    POSITIVE LOGITS
    peg
    0.26
    apter
    0.23
     caveat
    0.23
    clinical
    0.22
     hanging
    0.22
    perimental
    0.22
    大家ä¸Ģèµ·
    0.21
     resulting
    0.21
    ve
    0.21
     freeze
    0.21
    Activations Density 0.004%

    No Known Activations