© 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. 15-RESID-POST-AA
    11. 81333
    Prev
    Next
    INDEX
    Explanations

    Website building and software

    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_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
    Negative Logits
     Characteristics
    -0.07
     certain
    -0.07
    方方面面
    -0.06
    cantidad
    -0.06
    的颜色
    -0.06
     distance
    -0.06
     провер
    -0.06
    	random
    -0.06
     своем
    -0.06
     overse
    -0.06
    POSITIVE LOGITS
     Kenn
    0.07
    )";
↵
    0.07
    纠
    0.07
     Nazi
    0.07
     ży
    0.07
     aaa
    0.07
    좀
    0.07
    .UndefOr
    0.07
    洙
    0.07
    .commons
    0.06
    Activations Density 0.033%

    No Known Activations