© 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. 29746
    Prev
    Next
    INDEX
    Explanations

    text messaging

    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
    è¦ģç´§
    -0.11
    èĨĽ
    -0.10
     impuls
    -0.09
    assy
    -0.09
    byn
    -0.09
     ngủ
    -0.09
    åij¤
    -0.08
    raries
    -0.08
    æ·¡æ·¡
    -0.08
    (crate
    -0.08
    POSITIVE LOGITS
    ç¹ģ
    0.10
    ç¾İ好çĶŁæ´»
    0.08
    åħ°
    0.08
    å°ļ书
    0.08
    ÑĥÑī
    0.08
    mate
    0.08
    解æĶ¾
    0.08
    æ¡ij
    0.08
    æĸĩåĮĸéģĹ产
    0.08
    åįĥä¸ĩåĪ«
    0.08
    Activations Density 0.023%

    No Known Activations