© 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. 15-RESID-POST-AA
    6. 75210
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    階段
    -0.07
    ذه
    -0.07
    ��
    -0.07
    �
    -0.06
    think
    -0.06
     moving
    -0.06
    -season
    -0.06
    حل
    -0.06
    Routes
    -0.06
     Spr
    -0.06
    POSITIVE LOGITS
     humility
    0.07
    렐
    0.07
    مناز
    0.07
    市教育
    0.07
    billing
    0.07
    伋
    0.07
     wife
    0.07
     Maid
    0.07
    叮嘱
    0.06
     revived
    0.06
    Activations Density 0.087%

    No Known Activations