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. 131021
    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
    FW
    -0.07
     Finder
    -0.07
    𝑣
    -0.07
    	margin
    -0.07
    .right
    -0.07
    Scaler
    -0.07
    腹
    -0.07
    presso
    -0.07
     foods
    -0.07
    emouth
    -0.07
    POSITIVE LOGITS
    双赢
    0.07
    转型发展
    0.06
     istediği
    0.06
     miejs
    0.06
    竞争优势
    0.06
     undermines
    0.06
    .BackgroundColor
    0.06
     submarine
    0.06
    [min
    0.06
     DateTimeKind
    0.06
    Activations Density 0.089%

    No Known Activations