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

    Neuronpedia

    APICircuit 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. 71595
    Prev
    Next
    INDEX
    Explanations

    say "PE"

    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
     fry
    -0.07
    swift
    -0.07
    irsch
    -0.07
     chart
    -0.07
    	copy
    -0.07
    Join
    -0.06
    Discuss
    -0.06
     eyes
    -0.06
     course
    -0.06
    .addObject
    -0.06
    POSITIVE LOGITS
     Midlands
    0.07
    諾
    0.07
     Newark
    0.07
    っております
    0.07
     RGBA
    0.07
    ATFORM
    0.06
                                  ↵
    0.06
    武汉
    0.06
    ])+
    0.06
     anonymously
    0.06
    Activations Density 0.003%

    No Known Activations