© 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. 74273
    Prev
    Next
    INDEX
    Explanations

    Magic the Gathering

    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
    Cloud
    -0.08
     appDelegate
    -0.08
    ны
    -0.07
     Afghanistan
    -0.07
    olut
    -0.07
    iphone
    -0.07
    mys
    -0.07
    .tag
    -0.07
     cocina
    -0.07
    梧
    -0.06
    POSITIVE LOGITS
     cause
    0.07
     sell
    0.07
     spot
    0.07
    _buy
    0.06
     talking
    0.06
    _attention
    0.06
    _pemb
    0.06
    (optional
    0.06
     lief
    0.06
    边
    0.06
    Activations Density 0.012%

    No Known Activations