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. 19-RESID-POST-AA
    6. 7265
    Prev
    Next
    INDEX
    Explanations

    Code and file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    始
    -0.08
    (length
    -0.07
     בשנים
    -0.07
     Scalars
    -0.07
    enever
    -0.07
     Fabric
    -0.07
    ,message
    -0.07
    ╕
    -0.07
    ('.')
    -0.07
     Jarvis
    -0.06
    POSITIVE LOGITS
    �
    0.07
     Riy
    0.07
    刺客
    0.07
    水泥
    0.07
    可以用
    0.07
    -Un
    0.07
    提出的
    0.07
    ']))↵
    0.07
    ]}"↵
    0.06
    的游戏
    0.06
    Activations Density 0.523%

    No Known Activations