© 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. 34269
    Prev
    Next
    INDEX
    Explanations

    camper, RV, station, package, parks

    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
    çĺ¤
    -0.10
    寥
    -0.09
    æ¯ıæľĪ
    -0.09
    oko
    -0.09
    çĸ¤
    -0.09
     tin
    -0.09
    åĻľ
    -0.09
    umni
    -0.09
    æļ´é£İ
    -0.08
    itics
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸Ģ次
    0.09
    ÑĤек
    0.09
    .getActive
    0.09
    年纪
    0.09
    ardin
    0.08
    arshal
    0.08
    à¹ģ
    0.08
     Parkway
    0.08
    _SLEEP
    0.08
    溥
    0.08
    Activations Density 0.015%

    No Known Activations