© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 69987
    Prev
    Next
    INDEX
    Explanations

    contributors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bben
    -0.07
     הו
    -0.07
    chlor
    -0.07
     smash
    -0.07
    pch
    -0.07
    PRINT
    -0.07
     UserDao
    -0.07
     Door
    -0.07
     prejud
    -0.06
    顆
    -0.06
    POSITIVE LOGITS
     따른
    0.07
    変
    0.07
    石
    0.07
    اوي
    0.07
    륀
    0.07
    最常见的
    0.07
     journalist
    0.06
    הקמת
    0.06
     интерьер
    0.06
    下称
    0.06
    Activations Density 0.000%

    No Known Activations