© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20206
    Prev
    Next
    INDEX
    Explanations

    management excellence consulting projects

    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
    宵
    -0.11
    tep
    -0.10
    ·»
    -0.09
    hoot
    -0.09
    æĤĶ
    -0.09
    asure
    -0.09
    rant
    -0.09
    bil
    -0.09
    aller
    -0.09
    aine
    -0.09
    POSITIVE LOGITS
    andal
    0.09
    ovsky
    0.08
    彩èī²
    0.08
    å¯Ħ
    0.08
    OrUpdate
    0.08
    è¯Ģ
    0.08
    ìĵ¸
    0.08
     lean
    0.08
    /goto
    0.08
     Lean
    0.08
    Activations Density 0.035%

    No Known Activations