© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20935
    Prev
    Next
    INDEX
    Explanations

    center of mass inertia

    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
    çĸ²æĥ«
    -0.10
    æĭĽ
    -0.08
    åĬŁ
    -0.08
     Pu
    -0.08
     Active
    -0.08
     Ace
    -0.08
    Animate
    -0.08
    æĭĽåij¼
    -0.08
    çĸ²
    -0.08
    olum
    -0.08
    POSITIVE LOGITS
    éĩįå¿ĥ
    0.15
    平衡
    0.10
    干线
    0.10
    纵深
    0.10
    centroid
    0.09
    è²Į
    0.09
    峦
    0.09
    å·¥ä½ľå®¤
    0.09
    æ¯Ķéĩį
    0.09
    åĨħç½®
    0.09
    Activations Density 0.043%

    No Known Activations