© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 11-RESID-POST-AA
    11. 107388
    Prev
    Next
    INDEX
    Explanations

    Writing prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ){↵↵
    -0.08
    ages
    -0.07
    **(
    -0.07
     ){↵
    -0.07
    iveness
    -0.07
     oauth
    -0.07
    (ai
    -0.07
    acing
    -0.07
     naz
    -0.07
     corporate
    -0.07
    POSITIVE LOGITS
    clinic
    0.07
    那一天
    0.07
     ellas
    0.07
    𝒮
    0.07
    𝙩
    0.07
    (Photo
    0.06
    ＇
    0.06
    смотр
    0.06
    缡
    0.06
    젖
    0.06
    Activations Density 0.169%

    No Known Activations