© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62141
    Prev
    Next
    INDEX
    Explanations

    space locations or celestial bodies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
     Rid
    -0.09
    æ¸ħæ·¡
    -0.09
    åħħåĪĨä½ĵçİ°
    -0.09
    缸è§ģ
    -0.08
    èĪªå¤©
    -0.08
    家ä½ı
    -0.08
    å¤įåį°
    -0.08
    çĿĢä»ĸ
    -0.08
     Latvia
    -0.08
    åĨĴåĩº
    -0.08
    POSITIVE LOGITS
    æľįåĬ¡åķĨ
    0.09
    quist
    0.09
    é«ĺ度
    0.09
    åĬŁè¯¾
    0.09
    å°ĺ
    0.09
    -Sah
    0.09
    BOT
    0.08
    èĬ¹
    0.08
    æŀ¢çº½
    0.08
    âĨĶ
    0.08
    Activations Density 0.050%

    No Known Activations