© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11617
    Prev
    Next
    INDEX
    Explanations

    Israel, Middle East, Jews, policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    è´¨éĩıåĴĮ
    -0.25
    声èªī
    -0.23
    éĦ±
    -0.21
    çĨµ
    -0.21
    é¢ĨåĨĽ
    -0.21
    éĻª
    -0.20
    æįIJ
    -0.20
    èļģ
    -0.20
     Reputation
    -0.19
    æıĸ
    -0.19
    POSITIVE LOGITS
    ROME
    0.21
    convert
    0.20
    usalem
    0.19
    ARAM
    0.18
    iale
    0.18
    æķĻè®Ń
    0.18
    å¾Ģ
    0.18
    éĶĻ
    0.18
    ToLeft
    0.18
    plementation
    0.18
    Activations Density 0.006%

    No Known Activations