© 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. 62751
    Prev
    Next
    INDEX
    Explanations

    Cygwin permissions

    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
    èĤ¯
    -0.09
    çŀĮ
    -0.09
    缴è¾ĸ
    -0.09
    éĵĸ
    -0.09
    äºĨä¸Ģ份
    -0.09
     McKin
    -0.09
    åħ¶ä»ĸåĽ½å®¶
    -0.08
    æŶè£ħ
    -0.08
    æķ´é½IJ
    -0.08
    oky
    -0.08
    POSITIVE LOGITS
    ANA
    0.09
    ettings
    0.09
    å½
    0.09
    OrCreate
    0.09
    è§ģåĪ°
    0.08
    带
    0.08
    è¿Ĥ
    0.08
    å®ļ
    0.08
     evangel
    0.08
    ä¿Ń
    0.08
    Activations Density 0.021%

    No Known Activations