© 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. 47843
    Prev
    Next
    INDEX
    Explanations

    names followed by suffixes

    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
    æĦıè§ģåıįé¦Ī
    -0.10
    esser
    -0.10
     Everyday
    -0.09
    orna
    -0.09
    änger
    -0.08
    å¥Ĺ
    -0.08
    Toolkit
    -0.08
    件
    -0.08
    igli
    -0.08
    å½ĵåīįä½įç½®
    -0.08
    POSITIVE LOGITS
    sson
    0.10
    åºŁ
    0.09
    çĪµå£«
    0.09
    éĶ·
    0.09
    çĥŃè¡Ģ
    0.09
    fixture
    0.09
    äºĮ级
    0.08
    ä¸Ģä¸ĸ
    0.08
    代çIJĨ人
    0.08
    ä¸ī级
    0.08
    Activations Density 0.169%

    No Known Activations