© 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. 19-RESID-POST-AA
    11. 2033
    Prev
    Next
    INDEX
    Explanations

    ]

    np_max-act-logits · gemini-2.0-flash
    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
     aide
    -0.07
    בד
    -0.07
    diğiniz
    -0.06
    一颗
    -0.06
    ㌶
    -0.06
    arded
    -0.06
    ⇰
    -0.06
    嫒
    -0.06
    肤
    -0.06
     דעת
    -0.06
    POSITIVE LOGITS
    >';↵
    0.07
    关
    0.07
     blockade
    0.07
    ]'↵
    0.07
    𝚔
    0.07
    Mutation
    0.07
     Corinth
    0.07
     equalTo
    0.07
    opathy
    0.07
    Query
    0.07
    Activations Density 0.003%

    No Known Activations