© 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. 15-RESID-POST-AA
    11. 65642
    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
    Negative Logits
     discharge
    -0.07
    trainer
    -0.07
    宝马
    -0.07
     (*.
    -0.07
     setUp
    -0.07
    なか
    -0.06
    izza
    -0.06
    积水
    -0.06
    restore
    -0.06
     DEFINE
    -0.06
    POSITIVE LOGITS
     Greek
    0.08
    Ess
    0.07
     witnesses
    0.07
    �
    0.06
     empresas
    0.06
    .listFiles
    0.06
    There
    0.06
    endum
    0.06
    详细
    0.06
    	server
    0.06
    Activations Density 0.110%

    No Known Activations