© 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. 34369
    Prev
    Next
    INDEX
    Explanations

    competence, competency,

    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
    çĥ¬
    -0.10
    袱
    -0.10
    ä½ķåĨµ
    -0.10
    iness
    -0.09
    ette
    -0.09
    èŀį
    -0.09
    çģ¿çĥĤ
    -0.09
    weet
    -0.09
    enen
    -0.09
    ettes
    -0.08
    POSITIVE LOGITS
    -bodied
    0.10
    Jur
    0.09
     jurisdiction
    0.09
    imap
    0.09
    eder
    0.09
    ãģĤãģĴ
    0.08
    dia
    0.08
    ooter
    0.08
    ertia
    0.08
    eco
    0.08
    Activations Density 0.010%

    No Known Activations