© 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. 56537
    Prev
    Next
    INDEX
    Explanations

    jump lists

    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
    vious
    -0.10
    hood
    -0.10
    wards
    -0.09
    uron
    -0.09
    olumn
    -0.09
     podium
    -0.09
    enen
    -0.09
    uthor
    -0.09
    ´
    -0.09
     Sick
    -0.08
    POSITIVE LOGITS
    aroo
    0.15
    åĴĮå®ĮåĸĦ
    0.10
    ero
    0.10
    orial
    0.09
    æĪĽ
    0.09
    edList
    0.09
     Stout
    0.09
    licative
    0.09
    Insn
    0.09
    اث
    0.09
    Activations Density 0.014%

    No Known Activations