© 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. 11-RESID-POST-AA
    6. 26300
    Prev
    Next
    INDEX
    Explanations

    Possessive pronouns

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    公司
    -0.07
     Elle
    -0.07
     skirts
    -0.07
     Walls
    -0.07
    艚
    -0.07
    fte
    -0.07
     Mou
    -0.07
    .folder
    -0.07
     Fuller
    -0.07
     Mull
    -0.07
    POSITIVE LOGITS
    的战略
    0.07
    	Debug
    0.07
    崇拜
    0.07
    reshold
    0.07
     כמו
    0.06
    ประ
    0.06
    つな
    0.06
    itional
    0.06
    .XtraPrinting
    0.06
    _training
    0.06
    Activations Density 0.076%

    No Known Activations