Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88269
    Prev
    Next
    INDEX
    Explanations

    technical/scientific information

    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
     legis
    -0.08
    源源
    -0.07
    罘
    -0.07
    交汇
    -0.07
    urer
    -0.07
    	bt
    -0.07
    setVisible
    -0.07
    -pill
    -0.07
    律师
    -0.07
    老龄
    -0.07
    POSITIVE LOGITS
    鹑
    0.07
     Caucas
    0.07
    neas
    0.07
     NA
    0.06
    )];↵↵
    0.06
     ninguna
    0.06
     ámbito
    0.06
    .python
    0.06
     Bing
    0.06
     page
    0.06
    Activations Density 1.329%

    No Known Activations