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. 11-RESID-POST-AA
    6. 85767
    Prev
    Next
    INDEX
    Explanations

    ц

    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
     environ
    -0.07
     spiral
    -0.07
    ");↵↵↵
    -0.07
    不已
    -0.07
    维度
    -0.07
     tether
    -0.07
     zwei
    -0.07
    本期
    -0.07
     adip
    -0.07
    睡前
    -0.07
    POSITIVE LOGITS
     ц
    0.07
    сал
    0.07
    פג
    0.07
    �
    0.07
    struction
    0.06
    vc
    0.06
    院副院长
    0.06
    agra
    0.06
    说什么
    0.06
    ultural
    0.06
    Activations Density 0.023%

    No Known Activations