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. 19-RESID-POST-AA
    6. 129480
    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ours
    -0.08
    pointer
    -0.08
    abyrinth
    -0.07
     os
    -0.07
    (newUser
    -0.07
     truyền
    -0.07
    .magic
    -0.07
     Priority
    -0.07
    archivo
    -0.07
    조사
    -0.07
    POSITIVE LOGITS
     GANG
    0.07
    监理
    0.07
    (doc
    0.06
    ضبط
    0.06
     pimp
    0.06
    频道
    0.06
     ngươi
    0.06
     /↵
    0.06
    ))^
    0.06
     PREF
    0.06
    Activations Density 0.031%

    No Known Activations