© 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. 55620
    Prev
    Next
    INDEX
    Explanations

    it to start phrases

    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
    å°Ĩåħ¶
    -0.10
    ãĤ
    -0.09
    è¿ĺå°Ĩ
    -0.09
    è§ģåĪ°
    -0.08
    å¾Īå¤ļæŶåĢĻ
    -0.08
    å°±æĺ¯è¿Ļæł·
    -0.08
    hurst
    -0.08
    åīįæīĢ
    -0.08
    éĤ£è¾¹
    -0.08
    ä»ĸ们æĺ¯
    -0.08
    POSITIVE LOGITS
    ãģ¾ãģ¾
    0.10
    ByPrimaryKey
    0.10
    /th
    0.10
    æĬķåħ¥åĪ°
    0.09
    åħħå®ŀ
    0.09
    稽
    0.09
    åľ¨ä¸Ģèµ·
    0.09
    ilet
    0.09
    åľ¨ç½ijä¸Ĭ
    0.09
    æĪij们ä¸Ģèµ·
    0.09
    Activations Density 0.119%

    No Known Activations