© 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. 114589
    Prev
    Next
    INDEX
    Explanations

    Code/special characters

    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
     thriller
    -0.07
    ⮳
    -0.07
    Customer
    -0.07
    Rotor
    -0.06
    area
    -0.06
    iểu
    -0.06
    .mul
    -0.06
    serious
    -0.06
    섬
    -0.06
    ennie
    -0.06
    POSITIVE LOGITS
    GGLE
    0.08
    笔试
    0.08
     Drinking
    0.07
    WritableDatabase
    0.07
     pants
    0.07
     gab
    0.07
     pray
    0.07
    mit
    0.07
    突击
    0.07
     controllers
    0.06
    Activations Density 0.035%

    No Known Activations