© 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. 80387
    Prev
    Next
    INDEX
    Explanations

    Atari

    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
     Ses
    -0.08
    所
    -0.08
     kuk
    -0.08
     Jewel
    -0.07
     Cic
    -0.07
    itting
    -0.07
    Ip
    -0.07
    IR
    -0.07
    uvo
    -0.06
     majestic
    -0.06
    POSITIVE LOGITS
    Gary
    0.08
     impaired
    0.08
    واقع
    0.08
    上が
    0.07
    落后
    0.07
    >',↵
    0.07
     adjust
    0.07
    工业化
    0.07
    结束后
    0.07
    ]][
    0.07
    Activations Density 0.001%

    No Known Activations