© 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. 7-RESID-POST-AA
    6. 39816
    Prev
    Next
    INDEX
    Explanations

    judges

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鎏
    -0.08
    prof
    -0.08
    Pow
    -0.07
    皱
    -0.07
    OwnerId
    -0.07
    wizard
    -0.07
    ownt
    -0.07
     Mask
    -0.07
    weather
    -0.07
    world
    -0.07
    POSITIVE LOGITS
    	channel
    0.07
    .LA
    0.07
     Seminar
    0.07
     distribute
    0.07
     Arrange
    0.07
     Ends
    0.07
     anything
    0.07
    .Display
    0.07
    秧
    0.07
    啪
    0.07
    Activations Density 0.011%

    No Known Activations