© 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. 15-RESID-POST-AA
    11. 77707
    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يأتي
    -0.07
    urgent
    -0.07
    =");↵
    -0.07
    呗
    -0.07
     assort
    -0.07
    ]){↵
    -0.06
    	R
    -0.06
    ,R
    -0.06
    	write
    -0.06
    urer
    -0.06
    POSITIVE LOGITS
     tendency
    0.07
    这个游戏
    0.07
     בדרך
    0.07
     newsletters
    0.07
    传染病
    0.07
    Alabama
    0.07
     getObject
    0.07
    יכוי
    0.07
    imation
    0.07
    当
    0.07
    Activations Density 0.002%

    No Known Activations