© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 2364
    Prev
    Next
    INDEX
    Explanations

    go packages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    胍
    -0.07
     الاقتصادي
    -0.07
    뱔
    -0.07
     עסקי
    -0.07
     İnternet
    -0.07
    subscribe
    -0.07
    绤
    -0.07
    ebileceği
    -0.07
     tog
    -0.07
     حول
    -0.06
    POSITIVE LOGITS
    もら
    0.08
    .frequency
    0.08
     dod
    0.08
    杜绝
    0.07
    Dom
    0.07
     finishing
    0.06
     ongoing
    0.06
    咱们
    0.06
    いただいた
    0.06
    ポン
    0.06
    Activations Density 0.001%

    No Known Activations