© 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. 19-RESID-POST-AA
    6. 110728
    Prev
    Next
    INDEX
    Explanations

    #

    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
     sluggish
    -0.08
    /dir
    -0.07
     membuat
    -0.07
     bör
    -0.07
    升温
    -0.07
     eventos
    -0.07
    绘制
    -0.07
    ייצ
    -0.07
     umożli
    -0.07
     vitae
    -0.07
    POSITIVE LOGITS
    (coder
    0.07
     Refuge
    0.06
     loved
    0.06
    谝
    0.06
     mim
    0.06
     AZ
    0.06
    ,\
    0.06
    '){↵
    0.06
    )"},↵
    0.06
    .TestTools
    0.06
    Activations Density 0.000%

    No Known Activations