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. 87766
    Prev
    Next
    INDEX
    Explanations

    |

    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
    그
    -0.08
    每一个
    -0.07
    commit
    -0.07
    เต
    -0.07
    認
    -0.06
     radio
    -0.06
     KeyEvent
    -0.06
    ฒ
    -0.06
    诺贝尔
    -0.06
    _tA
    -0.06
    POSITIVE LOGITS
    YN
    0.08
    的要求
    0.07
    汕头
    0.07
    AGER
    0.07
     Enrollment
    0.07
     forcing
    0.07
    ITIONAL
    0.07
     seamlessly
    0.07
     designers
    0.07
    合わせ
    0.07
    Activations Density 0.003%

    No Known Activations