© 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. 53967
    Prev
    Next
    INDEX
    Explanations

    product descriptions/listings

    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
    lick
    -0.12
    sut
    -0.10
    .GetObject
    -0.10
    ignKey
    -0.09
    泡泡
    -0.09
    éŁŃèıľ
    -0.09
    ç²¾çĽĬæ±Ĥç²¾
    -0.08
    achu
    -0.08
    æĥ³æĥ³
    -0.08
    åĺĺ
    -0.08
    POSITIVE LOGITS
    å¼ıçļĦ
    0.10
     amp
    0.09
    å¼ı
    0.09
     womens
    0.08
    nings
    0.08
    bundle
    0.08
     bundle
    0.08
    çĶĦ
    0.08
     jac
    0.08
    perm
    0.08
    Activations Density 0.260%

    No Known Activations