© 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. 17016
    Prev
    Next
    INDEX
    Explanations

    address label or heading

    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
    ide
    -0.11
    çĬĬ
    -0.10
    ernote
    -0.09
     Swords
    -0.09
    æĢł
    -0.09
    ä»İ严
    -0.09
    abinet
    -0.09
    IDL
    -0.09
    ke
    -0.08
    .APPLICATION
    -0.08
    POSITIVE LOGITS
    (Address
    0.11
     address
    0.11
    åľ°åĿĢ
    0.10
    å¯Ħ
    0.10
     electr
    0.09
    æīĵä»Ĺ
    0.09
    VENT
    0.09
    дÑĢеÑģ
    0.09
    åĿĢ
    0.09
    .address
    0.08
    Activations Density 0.058%

    No Known Activations