© 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. 54222
    Prev
    Next
    INDEX
    Explanations

    North Dakota

    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
    æĭĬ
    -0.09
     Ny
    -0.09
    è¿ĺè®°å¾Ĺ
    -0.09
    oral
    -0.09
    æĭ
    -0.08
    念
    -0.08
    èĦĨ
    -0.08
    aji
    -0.08
    å®ŀè´¨æĢ§
    -0.08
    çıĬçijļ
    -0.08
    POSITIVE LOGITS
    بÙĪ
    0.10
    gage
    0.09
    éħ½
    0.09
    pent
    0.09
    _TRACE
    0.09
    çĶŁäº§çĶŁæ´»
    0.09
    å±ıéļľ
    0.08
    è¡·
    0.08
    æľīä¿¡å¿ĥ
    0.08
    иÑĤе
    0.08
    Activations Density 0.031%

    No Known Activations