© 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. 945
    Prev
    Next
    INDEX
    Explanations

    social media and tech platforms

    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
    +":
    -0.23
    ä¸ĢåĪĨéĴŁ
    -0.23
    ä¸įæĺ¯ä¸Ģ个
    -0.23
    æľªçŁ¥
    -0.22
     Shorts
    -0.22
    она
    -0.22
    åıijèµ·
    -0.22
    illus
    -0.21
    Inserted
    -0.21
    ç½ļ
    -0.21
    POSITIVE LOGITS
     Scient
    0.24
    ãĤ¸ãĥ§
    0.23
    æ°ijå¿ĥ
    0.23
     healthy
    0.21
    ä¼ģä¸ļæıIJä¾Ľ
    0.21
    åºĸ
    0.21
     pro
    0.21
     places
    0.21
     studios
    0.20
    _SR
    0.20
    Activations Density 0.001%

    No Known Activations