© 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. 39794
    Prev
    Next
    INDEX
    Explanations

    as well as

    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
    indo
    -0.09
    åŁºéĩij份é¢Ŀ
    -0.09
    _SI
    -0.09
    ç§ī
    -0.09
    .metamodel
    -0.09
    é³IJ
    -0.08
    æŀľæ±ģ
    -0.08
    å°¤åħ¶æĺ¯
    -0.08
    uran
    -0.08
    orr
    -0.08
    POSITIVE LOGITS
    çľĭå¾ħ
    0.10
    ä¸Ģæł·
    0.10
    ä¸ĩéĩĮ
    0.10
    claimer
    0.09
    åģ¶å°Ķ
    0.08
    èªĵ
    0.08
    éĤ£æł·
    0.08
    aid
    0.08
     previous
    0.08
    对å¾ħ
    0.08
    Activations Density 0.089%

    No Known Activations