© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19823
    Prev
    Next
    INDEX
    Explanations

    system and filter technology

    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¢Ń
    -0.10
    ritt
    -0.09
    uat
    -0.09
    交éĢļ
    -0.08
    交éĢļå·¥åħ·
    -0.08
     ún
    -0.08
    AGON
    -0.08
    cision
    -0.08
     radiation
    -0.08
    IDDLE
    -0.08
    POSITIVE LOGITS
    _filters
    0.10
    滤
    0.10
    èĹ»
    0.09
    è£ħç½®
    0.09
     filter
    0.09
    è¿ĩ滤
    0.09
     Filter
    0.09
    误åĮº
    0.09
    æī¹
    0.09
    åĽłåľ°åĪ¶å®ľ
    0.09
    Activations Density 0.198%

    No Known Activations