© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 17322
    Prev
    Next
    INDEX
    Explanations

    needle insertion and measurement devices

    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
     comp
    -0.09
    çħŀ
    -0.08
    0
    -0.08
    踩
    -0.08
    Aws
    -0.08
    6
    -0.08
    çĽĨ
    -0.08
    æĥķ
    -0.08
    ä¸Ĭå¹´
    -0.08
    iek
    -0.08
    POSITIVE LOGITS
    å°ĸ
    0.11
    éĿ¡
    0.10
    å°ıå¾®
    0.10
    èĹıçĿĢ
    0.10
    ichtig
    0.09
    嵯
    0.09
    ä¸īå®¶
    0.09
    ExecutionContext
    0.09
    ä¸Ģ次æĢ§
    0.09
     scre
    0.09
    Activations Density 0.352%

    No Known Activations