© 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. 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. 65371
    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
     escalated
    -0.07
    为自己
    -0.07
    특별
    -0.07
    핶
    -0.07
    .ForEach
    -0.07
    (Controller
    -0.07
    全新
    -0.06
     Ultimately
    -0.06
     самостоятельно
    -0.06
    etically
    -0.06
    POSITIVE LOGITS
     commerce
    0.08
     triang
    0.07
     intelligence
    0.07
    帮扶
    0.07
     dps
    0.07
    威慑
    0.07
    food
    0.07
    派遣
    0.07
     intercept
    0.07
     revelation
    0.07
    Activations Density 0.112%

    No Known Activations