© 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. 4621
    Prev
    Next
    INDEX
    Explanations

    many features

    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
    æ¬ł
    -0.10
    venues
    -0.09
    åIJĦåľ°
    -0.09
    çĮ¾
    -0.09
    suming
    -0.09
    ibri
    -0.09
    è£ģ
    -0.08
    .setContent
    -0.08
    esity
    -0.08
     Äijình
    -0.08
    POSITIVE LOGITS
     features
    0.12
     aspects
    0.11
     elements
    0.10
    梦幻
    0.10
    æ½Ń
    0.09
    çī¹å¾ģ
    0.09
    çī¹æĢ§
    0.09
    äºļè¿IJ
    0.09
    ä¼ĺçĤ¹
    0.09
    Features
    0.09
    Activations Density 0.149%

    No Known Activations