© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 48887
    Prev
    Next
    INDEX
    Explanations

    Code/Configuration files

    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
    多
    -0.07
    �始化
    -0.07
    可行
    -0.06
     email
    -0.06
     wichtig
    -0.06
    حذر
    -0.06
    zk
    -0.06
    ke
    -0.06
     Exec
    -0.06
     yardımc
    -0.06
    POSITIVE LOGITS
    geois
    0.07
     вой
    0.07
     glasses
    0.07
     abb
    0.07
    广场
    0.07
     пот
    0.07
     Raf
    0.07
    庄村
    0.07
     Polish
    0.07
     quasi
    0.07
    Activations Density 0.240%

    No Known Activations