© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 37349
    Prev
    Next
    INDEX
    Explanations

    McC names

    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
    å¤
    -0.11
    ault
    -0.10
    è¦ģä¹Ī
    -0.10
    enu
    -0.10
    ר×ĺ
    -0.09
    累累
    -0.09
    èĩ¾
    -0.09
    kits
    -0.08
    ãģĵãģ¨ãĤĤ
    -0.08
    estruct
    -0.08
    POSITIVE LOGITS
    ieren
    0.10
    vit
    0.09
    象
    0.09
    ism
    0.09
    aire
    0.08
    è¯Ľ
    0.08
    ista
    0.08
    ignal
    0.08
    讽
    0.08
    eds
    0.08
    Activations Density 0.005%

    No Known Activations