© 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. 3018
    Prev
    Next
    INDEX
    Explanations

    field collection and examination

    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
    éĴĪ
    -0.10
    ç®į
    -0.09
    éĩĿ
    -0.09
     Needle
    -0.09
    feeds
    -0.09
    åĮĿ
    -0.08
    çĹĽ
    -0.08
    pong
    -0.08
    _ARGUMENT
    -0.08
     needle
    -0.08
    POSITIVE LOGITS
    éĩİå¤ĸ
    0.15
    å®ŀåľ°
    0.13
    çĶ°éĩİ
    0.12
     field
    0.12
    éĩĩéĽĨ
    0.11
    (Field
    0.10
    åľ¨çİ°åľº
    0.10
    çİ°åľº
    0.10
    .field
    0.10
    çı¾åł´
    0.10
    Activations Density 0.094%

    No Known Activations