© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 7-RESID-POST-AA
    11. 59910
    Prev
    Next
    INDEX
    Explanations

    image

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .stage
    -0.07
    俵
    -0.07
     الجها
    -0.07
    ⻘
    -0.07
    �
    -0.06
    佼
    -0.06
    🅚
    -0.06
    龂
    -0.06
    三大阶段
    -0.06
     competency
    -0.06
    POSITIVE LOGITS
    私人
    0.07
    ,strong
    0.07
    ильно
    0.07
    )','
    0.07
    istant
    0.07
    _reservation
    0.07
    	pw
    0.07
     riots
    0.07
    Russia
    0.06
     compass
    0.06
    Activations Density 0.296%

    No Known Activations