© 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. 55840
    Prev
    Next
    INDEX
    Explanations

    job "titles"

    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
    esa
    -0.10
    ovel
    -0.09
    IRD
    -0.09
     Walnut
    -0.09
    .stamp
    -0.09
    hé
    -0.09
    ems
    -0.09
    bum
    -0.09
    æĤłä¹ħ
    -0.09
    hä
    -0.09
    POSITIVE LOGITS
    èī°å·¨
    0.09
    /job
    0.09
    åĥ®
    0.09
     accomplished
    0.08
    (Job
    0.08
    æĤ¬
    0.08
    horse
    0.08
    u
    0.08
    ัส
    0.08
    mans
    0.08
    Activations Density 0.051%

    No Known Activations