Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 130660
    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
    庖
    -0.07
    一大早
    -0.07
    的关系
    -0.07
     Cara
    -0.07
    EPHIR
    -0.07
     ámbito
    -0.07
    gmail
    -0.07
    マ
    -0.07
     younger
    -0.07
     polled
    -0.07
    POSITIVE LOGITS
    企业文化
    0.07
     Shen
    0.07
    ሽ
    0.07
     having
    0.06
    Elect
    0.06
    Τ
    0.06
    buttons
    0.06
     expected
    0.06
     yetiştir
    0.06
    .jetbrains
    0.06
    Activations Density 0.030%

    No Known Activations