© 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. 27305
    Prev
    Next
    INDEX
    Explanations

    Baja, Mexico, California, NAFTA

    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
    LOT
    -0.09
    éĥ½ä¸įæķ¢
    -0.09
    maid
    -0.08
     Pod
    -0.08
     pod
    -0.08
    pod
    -0.08
    gay
    -0.08
    å®ľå±ħ
    -0.08
    dal
    -0.08
    nel
    -0.08
    POSITIVE LOGITS
    ERING
    0.09
    edList
    0.09
    ibly
    0.09
     Orc
    0.09
    è¿ĻæĿ¡
    0.08
    åĨľå®¶
    0.08
    ëī´ìĬ¤
    0.08
     Californ
    0.08
    åĨįéĢł
    0.08
    ering
    0.08
    Activations Density 0.003%

    No Known Activations