© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59455
    Prev
    Next
    INDEX
    Explanations

    desert and valley geographical features

    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
    Negative Logits
    åĨ»
    -0.11
     Indo
    -0.09
    .Metro
    -0.09
    èĪ±
    -0.09
    æıIJæĹ©
    -0.09
    metro
    -0.08
    енÑĮ
    -0.08
    åħįéĻ¤
    -0.08
     fir
    -0.08
     laz
    -0.08
    POSITIVE LOGITS
    IDA
    0.10
    Wizard
    0.09
    mma
    0.09
    æ³ķå¸Ī
    0.09
    .di
    0.09
    çĶŁäº§åĴĮ
    0.08
    irected
    0.08
    综åIJĪæ²»çIJĨ
    0.08
    åįĩ
    0.08
    éĹ®ä»ĸ
    0.08
    Activations Density 0.123%

    No Known Activations