© 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. 19353
    Prev
    Next
    INDEX
    Explanations

    the [proper noun]

    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
    éĤ£éĩĮ
    -0.09
    è¿Ļä¸ªåľ°æĸ¹
    -0.08
    3
    -0.08
    à¹
    -0.08
    2
    -0.08
    7
    -0.08
    åIJĮå¿Ĺ们
    -0.08
    5
    -0.08
    1
    -0.08
    oval
    -0.07
    POSITIVE LOGITS
    ibold
    0.10
    çŀ°
    0.10
    ä¿Ŀå®ī
    0.09
    andles
    0.09
    rottle
    0.09
     Rex
    0.09
    èIJ¥ä¸ļ
    0.09
    aviors
    0.09
    æį¢åıĸ
    0.09
    åĩĨç¡®æĢ§
    0.09
    Activations Density 0.024%

    No Known Activations