© 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. 2667
    Prev
    Next
    INDEX
    Explanations

    Plymouth, Springfield, Peoria

    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
     Spoon
    -0.10
    ake
    -0.10
     populous
    -0.09
    diff
    -0.09
    ble
    -0.09
    æ®ĸ
    -0.08
    ulty
    -0.08
    辫
    -0.08
    å¤Ķ
    -0.08
    ë¸Ķ
    -0.08
    POSITIVE LOGITS
    بÙĥ
    0.08
    /tty
    0.08
    ettings
    0.08
    éļİ
    0.08
    sea
    0.08
     Sure
    0.08
    èĪªæµ·
    0.08
    æĹ°
    0.08
    omens
    0.08
    ermo
    0.08
    Activations Density 0.002%

    No Known Activations