© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 44973
    Prev
    Next
    INDEX
    Explanations

    ulated

    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
     Duplicate
    -0.07
    華
    -0.07
    자
    -0.07
    华
    -0.06
     discrim
    -0.06
    พ
    -0.06
    創
    -0.06
     insufficient
    -0.06
     bibliography
    -0.06
    Private
    -0.06
    POSITIVE LOGITS
    Chron
    0.07
     hated
    0.07
    .dependencies
    0.07
     coats
    0.07
     AssemblyProduct
    0.07
    。www
    0.07
    웛
    0.07
    حتاج
    0.07
    瘭
    0.06
    oky
    0.06
    Activations Density 0.160%

    No Known Activations