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. 130902
    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
    Ik
    -0.07
    发现自己
    -0.07
    👴
    -0.07
    día
    -0.07
     være
    -0.06
     figura
    -0.06
    مرض
    -0.06
    자가
    -0.06
    jourd
    -0.06
    يض
    -0.06
    POSITIVE LOGITS
    会议精神
    0.07
    _context
    0.07
    	HX
    0.07
     amenities
    0.07
     Feinstein
    0.07
    -responsive
    0.07
     SH
    0.07
     CUT
    0.07
    Plans
    0.07
     Trinity
    0.07
    Activations Density 0.008%

    No Known Activations