© 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. 1591
    Prev
    Next
    INDEX
    Explanations

    version numbers or identifiers

    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
     sharper
    -0.26
    ucus
    -0.23
    /dc
    -0.23
    LANGUAGE
    -0.22
    hti
    -0.22
    ®,
    -0.22
    IQ
    -0.21
     jou
    -0.21
    WARE
    -0.21
    ACES
    -0.20
    POSITIVE LOGITS
    ä¸įéĶĻ
    0.23
    lib
    0.23
    å¾Ĺ好
    0.23
    è´Ń
    0.23
    没éĶĻ
    0.22
    æģ¼
    0.22
    çĺ¦
    0.21
    pret
    0.21
     verge
    0.21
    æĭŁ
    0.20
    Activations Density 0.173%

    No Known Activations