© 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. 73957
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    줌
    -0.07
    WithType
    -0.07
    됨
    -0.07
    年
    -0.06
    ובר
    -0.06
     וי
    -0.06
     test
    -0.06
    🤞
    -0.06
     dam
    -0.06
    Module
    -0.06
    POSITIVE LOGITS
     deceived
    0.08
    それを
    0.07
    itates
    0.07
    acción
    0.07
     letzten
    0.07
    restrict
    0.07
     그것을
    0.07
    偏离
    0.07
     annihil
    0.07
     Lansing
    0.07
    Activations Density 0.012%

    No Known Activations