© 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. 3790
    Prev
    Next
    INDEX
    Explanations

    no surprise

    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
     Hend
    -0.10
    çĥĻ
    -0.09
    å¤Ł
    -0.09
    بÙĬÙĨ
    -0.09
    ToDevice
    -0.08
    èī¯
    -0.08
    Borders
    -0.08
    çħ½
    -0.08
     hopefully
    -0.07
    hea
    -0.07
    POSITIVE LOGITS
    é¢ĦæĸĻ
    0.14
    å¿ħçĦ¶
    0.12
     predictable
    0.12
     predict
    0.11
     inevitable
    0.11
     inev
    0.10
    å·²ä¹ħ
    0.10
    çŁ¥æĥħ
    0.10
    å·²ä¹ħçļĦ
    0.10
    ä¼ı
    0.10
    Activations Density 0.059%

    No Known Activations