© 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. 23164
    Prev
    Next
    INDEX
    Explanations

    full image listing copyright HD

    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
    prung
    -0.10
    éªIJ
    -0.10
    ijľ
    -0.09
    fullscreen
    -0.09
    åŃĺéĩı
    -0.09
     tạp
    -0.09
    åIJįé¢Ŀ
    -0.09
    å³Ĵ
    -0.09
    ãĥŃãĥ¼
    -0.08
    &M
    -0.08
    POSITIVE LOGITS
    çŁ¥
    0.09
    apes
    0.09
    iles
    0.08
    .retry
    0.08
    åľ¨åĮĹ京
    0.08
    odes
    0.08
    åĹĮ
    0.08
    odos
    0.08
    é¹°
    0.08
    _terms
    0.08
    Activations Density 0.018%

    No Known Activations