© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 35591
    Prev
    Next
    INDEX
    Explanations

    presented

    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
     response
    -0.07
     Spa
    -0.07
    Park
    -0.07
     protest
    -0.07
    atom
    -0.07
     resolves
    -0.06
    erv
    -0.06
     loads
    -0.06
     Space
    -0.06
     iterators
    -0.06
    POSITIVE LOGITS
    칙
    0.08
    kę
    0.07
     contributes
    0.07
    רכי
    0.07
    ��
    0.07
    יני
    0.07
    dux
    0.07
    ียง
    0.07
    党风廉政
    0.07
     الشركات
    0.07
    Activations Density 0.011%

    No Known Activations