© 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. 39857
    Prev
    Next
    INDEX
    Explanations

    goals scored

    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¯ķçĤ¹å·¥ä½ľ
    -0.11
    éªĽ
    -0.10
    楣
    -0.10
    说å®ŀ
    -0.10
    èģĶ社
    -0.10
    追赶
    -0.10
    uum
    -0.10
    åı¶åŃIJ
    -0.10
    产åĮº
    -0.09
    è¹ij
    -0.09
    POSITIVE LOGITS
    posit
    0.08
    tring
    0.08
    大象
    0.08
    çľ¼
    0.08
    à¹īà¸Ńย
    0.08
    .deb
    0.08
    ocs
    0.08
    PN
    0.08
    ä¸Ģ个å¤ļæľĪ
    0.07
    çī¢
    0.07
    Activations Density 0.034%

    No Known Activations