© 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. 33839
    Prev
    Next
    INDEX
    Explanations

    control

    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
    æĥ¨
    -0.10
    æī£
    -0.08
    åī²
    -0.08
     cro
    -0.08
    å´©
    -0.08
    æ±ł
    -0.08
    åģļå®Į
    -0.08
    æ¡Į
    -0.08
    计
    -0.08
     mate
    -0.08
    POSITIVE LOGITS
    å®ŀéĻħæݧåĪ¶
    0.14
    éĹŃçݯ
    0.12
    æݧåĪ¶åĻ¨
    0.11
    æݧåĪ¶ç³»ç»Ł
    0.11
    icontrol
    0.10
     Controller
    0.10
    /ros
    0.10
     controller
    0.10
    ä¼
    0.09
    controller
    0.09
    Activations Density 0.207%

    No Known Activations