© 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. 12428
    Prev
    Next
    INDEX
    Explanations

    avocado

    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_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
    创投
    -0.08
     داخل
    -0.07
     intuit
    -0.07
    鼱
    -0.07
     bande
    -0.07
     Yorkshire
    -0.07
    bread
    -0.07
     Prince
    -0.07
     fatt
    -0.07
    owości
    -0.07
    POSITIVE LOGITS
     tabBar
    0.08
     :)↵↵
    0.08
     standards
    0.07
    通
    0.07
    -local
    0.07
    full
    0.07
    -application
    0.07
    ka
    0.07
     usually
    0.07
    Ps
    0.07
    Activations Density 0.002%

    No Known Activations