© 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. 11-RESID-POST-AA
    6. 91964
    Prev
    Next
    INDEX
    Explanations

    Drag and drop functionality

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ード
    -0.07
    慶
    -0.07
     network
    -0.07
    😙
    -0.07
    ביניהם
    -0.06
     Chúng
    -0.06
     wz
    -0.06
     Conte
    -0.06
    eyed
    -0.06
    okies
    -0.06
    POSITIVE LOGITS
     Scar
    0.07
     just
    0.07
    טרה
    0.07
    习惯
    0.07
     Wy
    0.07
     taxes
    0.07
     Esk
    0.07
     ISBN
    0.07
    ią
    0.07
     Until
    0.06
    Activations Density 0.011%

    No Known Activations