© 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. 3779
    Prev
    Next
    INDEX
    Explanations

    hay baler

    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
    .shtml
    -0.10
    å¼ķæĵİ
    -0.08
    å¸ĪçĶŁ
    -0.08
    scriptions
    -0.08
    åĮĨåĮĨ
    -0.08
    Bounds
    -0.08
     Sink
    -0.08
    æĮ¤
    -0.08
    +_
    -0.08
    æģ¯
    -0.08
    POSITIVE LOGITS
    æįĨ
    0.10
    æ·¡åĮĸ
    0.10
    æľĢå°ij
    0.10
    æīĵåĮħ
    0.10
    erot
    0.09
    èĩªåĪ¶
    0.09
    èķ¤
    0.09
    å°ı麦
    0.09
    ogl
    0.09
     ÃŃt
    0.09
    Activations Density 0.085%

    No Known Activations