Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130681
    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
    ITTLE
    -0.07
    صاح
    -0.07
     '\\
    -0.07
    在我看来
    -0.07
     snaps
    -0.06
     เพราะ
    -0.06
    衣
    -0.06
     Heavy
    -0.06
     bởi
    -0.06
    ﻴ
    -0.06
    POSITIVE LOGITS
    地毯
    0.08
    andes
    0.08
    \Exception
    0.08
     redund
    0.07
     succinct
    0.07
    ຖ
    0.07
    ᕦ
    0.07
    quez
    0.07
    常德
    0.07
    _db
    0.07
    Activations Density 0.022%

    No Known Activations