© 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. 76490
    Prev
    Next
    INDEX
    Explanations

    Lady

    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
     triple
    -0.07
     Solver
    -0.07
     SIL
    -0.07
     "[%
    -0.07
    بر
    -0.07
     relie
    -0.07
     SPF
    -0.07
     spur
    -0.06
     '|
    -0.06
    	response
    -0.06
    POSITIVE LOGITS
     WebElement
    0.08
     Lady
    0.07
    .getOrElse
    0.07
    .Iterator
    0.07
    Lady
    0.07
    催化
    0.07
     lượng
    0.07
     העליון
    0.07
    尴
    0.06
    ahkan
    0.06
    Activations Density 0.002%

    No Known Activations