© 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. 62300
    Prev
    Next
    INDEX
    Explanations

    resort locations and types

    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
    ulle
    -0.10
    ammer
    -0.10
     اÙĦتارÙĬØ®
    -0.09
    raison
    -0.09
    hift
    -0.09
    峡
    -0.09
    åİĭå®ŀ
    -0.09
    inz
    -0.08
     ÑĥÑģÑĤÑĢойÑģÑĤва
    -0.08
    ãĥ¼ãĥ
    -0.08
    POSITIVE LOGITS
    acular
    0.11
    acles
    0.10
    swith
    0.09
    ï¾ŀ
    0.09
    zend
    0.09
    ively
    0.09
    cription
    0.09
    sw
    0.08
    èı°
    0.08
    scr
    0.08
    Activations Density 0.005%

    No Known Activations