© 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. 58495
    Prev
    Next
    INDEX
    Explanations

    insider, insiders

    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
    é¦ĸä½į
    -0.10
    crest
    -0.10
    -bodied
    -0.10
    ains
    -0.09
    sam
    -0.09
     Capitals
    -0.09
    ç¼ģ
    -0.09
    imals
    -0.09
    urent
    -0.09
    çĽĨåľ°
    -0.09
    POSITIVE LOGITS
    rush
    0.10
    åĢij
    0.10
    ages
    0.10
    大çīĩ
    0.09
    ises
    0.09
    duct
    0.09
    ly
    0.09
    åĽ¹
    0.09
    omatic
    0.09
    -most
    0.09
    Activations Density 0.002%

    No Known Activations