© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75882
    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
    �单
    -0.08
    _scenario
    -0.07
    מידע
    -0.07
    国会
    -0.07
     dataSet
    -0.07
    ことは
    -0.07
    득
    -0.07
    发展模式
    -0.07
     kv
    -0.07
     PHI
    -0.06
    POSITIVE LOGITS
    自觉
    0.06
    -popup
    0.06
    落地
    0.06
    getParameter
    0.06
    ика
    0.06
     enclosing
    0.06
    .escape
    0.06
    可靠
    0.06
    只要有
    0.06
     mix
    0.06
    Activations Density 0.041%

    No Known Activations