© 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. 95709
    Prev
    Next
    INDEX
    Explanations

    include

    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
     prepare
    -0.07
    ellation
    -0.07
     Vert
    -0.07
    walk
    -0.07
    ors
    -0.07
    [position
    -0.06
    打击
    -0.06
    走访
    -0.06
    珩
    -0.06
    phi
    -0.06
    POSITIVE LOGITS
    עים
    0.08
    pecific
    0.07
     diferentes
    0.07
     yayınlan
    0.07
     football
    0.07
     contradictory
    0.07
     pacientes
    0.07
     superiority
    0.06
     plaque
    0.06
     capitalism
    0.06
    Activations Density 0.014%

    No Known Activations