© 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. 7579
    Prev
    Next
    INDEX
    Explanations

    macrobi, macroscop, macroceph, macroglia, macro

    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
    jie
    -0.10
    otted
    -0.09
    ared
    -0.09
    recv
    -0.09
    azz
    -0.09
    jee
    -0.08
    ted
    -0.08
    apro
    -0.08
    å½·
    -0.08
    razil
    -0.08
    POSITIVE LOGITS
    -minded
    0.13
    scopic
    0.13
     minded
    0.13
    嵬
    0.11
    itud
    0.10
    umat
    0.10
    主ä¹īèĢħ
    0.09
    евиÑĩ
    0.09
    CESS
    0.09
    illary
    0.09
    Activations Density 0.040%

    No Known Activations