© 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. 17190
    Prev
    Next
    INDEX
    Explanations

    and so on/forth

    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
     meanwhile
    -0.11
     nonetheless
    -0.10
    erer
    -0.10
    æĻ°
    -0.10
    è¿ħ
    -0.09
     nevertheless
    -0.09
     sourceMapping
    -0.09
    cheid
    -0.09
    ickers
    -0.09
    ENA
    -0.09
    POSITIVE LOGITS
     ilk
    0.09
    lund
    0.09
    é¢ĺ主
    0.09
    åħ¶ä»ĸçļĦ
    0.08
    rim
    0.08
    åįĪåIJİ
    0.08
    лиÑĤ
    0.08
    åĪĨæł¡
    0.08
     forth
    0.08
    RIX
    0.08
    Activations Density 0.021%

    No Known Activations