© 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. 21697
    Prev
    Next
    INDEX
    Explanations

    environment, climate, green initiatives

    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
    elter
    -0.10
    颦
    -0.10
    æµ·è¾¹
    -0.10
    海滨
    -0.10
    éħįå¥Ĺ设æĸ½
    -0.09
    æľīåĪ©
    -0.09
    æľįåĬ¡ä½ĵç³»
    -0.09
    é¹ħ
    -0.09
    PTY
    -0.09
    çĮľæĥ³
    -0.09
    POSITIVE LOGITS
    åľ°çIJĥ
    0.10
    bul
    0.10
    仲
    0.09
    衲
    0.09
    èĬĤ约
    0.09
    irth
    0.08
     Bj
    0.08
    (Environment
    0.08
     bul
    0.08
    森
    0.08
    Activations Density 0.048%

    No Known Activations