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. 130951
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     illuminate
    -0.08
    }:${
    -0.08
     ignite
    -0.07
     crianças
    -0.07
    אישור
    -0.07
     conexao
    -0.07
     phục
    -0.07
     addons
    -0.07
    锶
    -0.07
    筏
    -0.07
    POSITIVE LOGITS
    _SL
    0.07
    asury
    0.07
    		 
    0.07
    '',
    0.07
    'url
    0.07
    PART
    0.07
     ap
    0.07
    >',
    0.07
    切
    0.07
    :UIButtonTypeCustom
    0.07
    Activations Density 0.001%

    No Known Activations