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. 49400
    Prev
    Next
    INDEX
    Explanations

    real-time web communication

    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
    REN
    -0.07
     ov
    -0.07
     leicht
    -0.07
    有一些
    -0.07
    (val
    -0.07
    Thunder
    -0.06
     thankful
    -0.06
    缴纳
    -0.06
     miệng
    -0.06
    Setup
    -0.06
    POSITIVE LOGITS
     '/')
    0.08
    ")));↵
    0.07
     specified
    0.07
     bü
    0.07
    SFML
    0.07
    ){}↵
    0.07
    -motion
    0.07
    ቢ
    0.07
     fileInfo
    0.07
    empresa
    0.07
    Activations Density 0.031%

    No Known Activations