© 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. 50567
    Prev
    Next
    INDEX
    Explanations

    proposal outlines, concerns, or is

    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
    çĦ¶æĺ¯
    -0.10
    yard
    -0.10
    iating
    -0.10
    uate
    -0.09
    ening
    -0.09
    åĿļæĮģä¸įæĩĪ
    -0.09
    nin
    -0.09
    ãģĦãģĨ
    -0.09
    ention
    -0.09
    yt
    -0.09
    POSITIVE LOGITS
    à¹ģà¸Ļะ
    0.13
    ive
    0.10
    ÑĥÑģÑĤ
    0.10
    ../
    0.09
    osals
    0.09
    맥
    0.09
    etary
    0.09
    IK
    0.09
    IAS
    0.08
    mium
    0.08
    Activations Density 0.024%

    No Known Activations