© 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. 12262
    Prev
    Next
    INDEX
    Explanations

    free shipping, delivery, software, download

    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
    èį¤
    -0.09
    inho
    -0.09
    箪
    -0.09
    鼷
    -0.08
    åīįä¸įä¹ħ
    -0.08
    类产åĵģ
    -0.08
    è´©åįĸ
    -0.08
    å¾Ī好
    -0.08
    .blogspot
    -0.08
    awah
    -0.08
    POSITIVE LOGITS
    /free
    0.16
     Free
    0.13
    Free
    0.12
     free
    0.12
     FREE
    0.12
    -Free
    0.12
    _free
    0.12
    .Free
    0.12
    _FREE
    0.11
    åħįè´¹
    0.11
    Activations Density 0.026%

    No Known Activations