© 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. 113629
    Prev
    Next
    INDEX
    Explanations

    role-playing games

    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
    儇
    -0.07
     raise
    -0.07
    冷水
    -0.07
    の中
    -0.07
    Chuck
    -0.07
     #__
    -0.07
    淙
    -0.07
    主城区
    -0.07
    潏
    -0.06
    傍
    -0.06
    POSITIVE LOGITS
    Prot
    0.07
    ált
    0.07
     אחרי
    0.07
     editText
    0.07
     Task
    0.07
    _ES
    0.07
    .Permission
    0.07
    原来是
    0.07
    .account
    0.06
    _fft
    0.06
    Activations Density 0.019%

    No Known Activations