© 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. 15-RESID-POST-AA
    11. 30529
    Prev
    Next
    INDEX
    Explanations

    series

    np_max-act · gemini-2.0-flash
    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
    惦
    -0.08
    UEST
    -0.07
    fuck
    -0.07
    uchsia
    -0.07
    %x
    -0.07
    Ử
    -0.07
    ulner
    -0.07
     Antarctica
    -0.07
    Qu
    -0.07
    ONGO
    -0.07
    POSITIVE LOGITS
     series
    0.09
    系列
    0.08
    申し込み
    0.07
    位列
    0.07
    的问题
    0.07
    -from
    0.07
    メリット
    0.07
    至於
    0.07
     Drawer
    0.07
    席卷
    0.07
    Activations Density 0.031%

    No Known Activations