© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 78428
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ẽ
    -0.08
     respects
    -0.08
     นอกจาก
    -0.07
    变为
    -0.07
    将成为
    -0.07
    TN
    -0.07
    抗击疫情
    -0.07
    孝
    -0.07
    ')}}↵
    -0.06
    ﰌ
    -0.06
    POSITIVE LOGITS
     Attorney
    0.08
    /search
    0.07
     NEW
    0.07
     пунк
    0.07
     ober
    0.07
    料理
    0.07
     ofstream
    0.07
    numero
    0.07
    (iterator
    0.07
     Geld
    0.07
    Activations Density 0.001%

    No Known Activations