© 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. 23-RESID-POST-AA
    11. 129336
    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Acquisition
    -0.08
    rish
    -0.07
    roman
    -0.07
    摄
    -0.07
                         ↵
    -0.07
    前辈
    -0.07
     cavalry
    -0.07
    getti
    -0.07
    祖
    -0.07
     Neville
    -0.07
    POSITIVE LOGITS
    إعل
    0.07
    צביע
    0.07
     Республик
    0.07
    �
    0.07
    โรงพยา
    0.07
    ampling
    0.07
     PARAMETERS
    0.07
    /themes
    0.07
    سياسات
    0.07
    submenu
    0.07
    Activations Density 0.001%

    No Known Activations