© 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. 2368
    Prev
    Next
    INDEX
    Explanations

    Pixar, DVR, Avaya, Corporation

    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
    liches
    -0.22
     Corinth
    -0.22
    steel
    -0.21
    幺
    -0.21
    acobian
    -0.21
    spirit
    -0.20
    å¹ħ
    -0.20
    uste
    -0.20
    å»Ĭ
    -0.20
    éĤ£ä¸ªäºº
    -0.20
    POSITIVE LOGITS
     systems
    0.25
    ãĤ·ãĤ¹ãĥĨãĥł
    0.25
     DVR
    0.25
     popcorn
    0.24
     movies
    0.24
     smart
    0.24
    éģ¥æݧ
    0.24
    ç³»ç»Ł
    0.24
    ç³»ç»ŁçļĦ
    0.24
    imit
    0.23
    Activations Density 0.002%

    No Known Activations