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. 130738
    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
    不是
    -0.07
    もち
    -0.07
    𝚎
    -0.07
     Cohen
    -0.07
     Neither
    -0.07
     Pan
    -0.07
    late
    -0.07
     Chí
    -0.07
     Serious
    -0.07
    愿意
    -0.07
    POSITIVE LOGITS
    dataArray
    0.08
    .atom
    0.07
     klient
    0.07
    _feedback
    0.07
     interact
    0.07
     OWNER
    0.07
     umożli
    0.06
     apologized
    0.06
    stops
    0.06
    regist
    0.06
    Activations Density 0.001%

    No Known Activations