© 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. 11-RESID-POST-AA
    6. 74619
    Prev
    Next
    INDEX
    Explanations

    random blog posts/articles

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irsch
    -0.07
     itemList
    -0.07
     Zug
    -0.07
     Learn
    -0.06
    fabs
    -0.06
    htags
    -0.06
    урс
    -0.06
    ﮉ
    -0.06
    اتحاد
    -0.06
     childbirth
    -0.06
    POSITIVE LOGITS
    :Any
    0.08
    =j
    0.07
     Fuk
    0.07
     сдел
    0.07
    no
    0.07
     seine
    0.07
     pca
    0.07
    飙
    0.07
     دقائق
    0.07
     بلا
    0.07
    Activations Density 0.042%

    No Known Activations