© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51646
    Prev
    Next
    INDEX
    Explanations

    9 or nine

    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
    agher
    -0.10
     Zus
    -0.09
    urer
    -0.08
    æĻ°
    -0.08
    åĢ©
    -0.08
    é¢Į
    -0.08
    æ²ģ
    -0.08
    orne
    -0.08
    åıĮèħ¿
    -0.08
    让åѦçĶŁ
    -0.08
    POSITIVE LOGITS
    æľĿ
    0.12
    veh
    0.10
    ruc
    0.09
    åĩĨæŶ
    0.08
    ï¸
    0.08
    çīĸ
    0.08
    æ¤ħ
    0.08
     thơ
    0.08
    åħ¸ç¤¼
    0.08
    侯
    0.08
    Activations Density 0.125%

    No Known Activations