© 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. 10065
    Prev
    Next
    INDEX
    Explanations

    monetary compensation commission affiliate referral

    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
    ingles
    -0.11
    æ²»
    -0.10
    缩
    -0.09
    é¢Ħ约
    -0.09
    çľĦ
    -0.09
    BoxLayout
    -0.09
    主ç¼ĸ
    -0.08
     abbrev
    -0.08
    主å¸Ń
    -0.08
    åĨ¶
    -0.08
    POSITIVE LOGITS
    ä½£éĩij
    0.12
     referral
    0.11
    æĭĽçĶŁ
    0.10
     комиÑģÑģи
    0.10
    ä¸Ńä»ĭ
    0.10
    edium
    0.10
    æݨèįIJ
    0.09
     Reward
    0.09
    ä½£
    0.09
     getenv
    0.08
    Activations Density 0.095%

    No Known Activations