© 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. 61340
    Prev
    Next
    INDEX
    Explanations

    under or beneath

    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
     пиÑĤаниÑı
    -0.10
    ä¾Ľç»Ļ侧
    -0.10
    ä¸Ģç¬Ķ
    -0.09
    害
    -0.09
    åľ¨éĩĮéĿ¢
    -0.09
     иÑģп
    -0.09
    éļĶçĿĢ
    -0.09
    æĶ»åĿļ
    -0.09
    ãģ«åħ¥ãģ£ãģŁ
    -0.08
    éŀĭ
    -0.08
    POSITIVE LOGITS
    éĻįèIJ½
    0.09
    èĭ¥æĤ¨
    0.08
    é²ľèĬ±
    0.08
    æĹĹ
    0.08
     overhead
    0.08
    UB
    0.08
    bau
    0.08
    æłĩè¯Ń
    0.08
    æŀ¶
    0.08
    utral
    0.08
    Activations Density 0.159%

    No Known Activations