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. 130775
    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
     Bras
    -0.07
    aiser
    -0.07
     trans
    -0.07
     Approx
    -0.06
    אמנות
    -0.06
    特有的
    -0.06
    湎
    -0.06
    ല
    -0.06
    墡
    -0.06
     이루어
    -0.06
    POSITIVE LOGITS
    سرعة
    0.07
    分局
    0.07
    ทำความสะอาด
    0.07
     barrels
    0.07
    变速箱
    0.07
     Unit
    0.07
    税务局
    0.07
    ☝
    0.07
     Kara
    0.07
    Wenn
    0.06
    Activations Density 0.061%

    No Known Activations