© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15-RESID-POST-AA
    6. 23290
    Prev
    Next
    INDEX
    Explanations

    mechanical components

    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
    迷失
    -0.07
    リスク
    -0.07
    Doctors
    -0.07
    ホテル
    -0.07
    pokemon
    -0.06
    ConfigurationException
    -0.06
     turbines
    -0.06
    机器人
    -0.06
     SSR
    -0.06
    훾
    -0.06
    POSITIVE LOGITS
    ]);↵
    0.07
    li
    0.07
    翳
    0.07
    回收
    0.06
     solves
    0.06
    option
    0.06
     Frame
    0.06
    FX
    0.06
     idea
    0.06
     Form
    0.06
    Activations Density 0.080%

    No Known Activations