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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 56382
    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_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
     assured
    -0.08
    角度
    -0.07
     creo
    -0.07
     respect
    -0.07
     consultants
    -0.07
    十个
    -0.07
     rebell
    -0.06
     convex
    -0.06
    /ad
    -0.06
     хоч
    -0.06
    POSITIVE LOGITS
    בית
    0.08
     Locker
    0.08
     컴퓨
    0.07
    岢
    0.07
    .liferay
    0.07
     BCHP
    0.07
    strcpy
    0.07
    얗
    0.07
    Ᏼ
    0.07
    AppDelegate
    0.07
    Activations Density 0.017%

    No Known Activations