© 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. 29270
    Prev
    Next
    INDEX
    Explanations

    incisors

    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
     contends
    -0.09
    ItemType
    -0.07
    胝
    -0.07
    楞
    -0.07
     errone
    -0.07
    耘
    -0.07
    setTitle
    -0.07
     Huntington
    -0.07
     Nation
    -0.07
    .Exceptions
    -0.07
    POSITIVE LOGITS
     inhibition
    0.07
    ذ
    0.07
    ihat
    0.07
    и
    0.07
     После
    0.07
    穿上
    0.07
     widest
    0.07
    	define
    0.07
     Book
    0.06
    ipsis
    0.06
    Activations Density 0.001%

    No Known Activations