© 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. 39847
    Prev
    Next
    INDEX
    Explanations

    takeover or hack

    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
    åĪĨå±Ģ
    -0.08
     fond
    -0.08
    æĸĩåĮĸ建设
    -0.08
    äºĪ
    -0.08
    ucci
    -0.08
    çĻĸ
    -0.08
     koÅŁ
    -0.08
    .Cond
    -0.08
     Lair
    -0.08
    .hover
    -0.08
    POSITIVE LOGITS
    æݥ管
    0.15
     hij
    0.14
     takeover
    0.12
     Hij
    0.12
    åįłé¢Ĩ
    0.11
    鸳
    0.11
    èµĭèĥ½
    0.10
    é²ĩ
    0.10
    åħ¥ä¾µ
    0.10
    (Control
    0.10
    Activations Density 0.115%

    No Known Activations