© 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. 6572
    Prev
    Next
    INDEX
    Explanations

    verb tenses

    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
     freaking
    -0.07
    Imp
    -0.07
    鄗
    -0.06
    𝐽
    -0.06
     ignored
    -0.06
    Ẵ
    -0.06
    ㋯
    -0.06
    andex
    -0.06
    忘
    -0.06
    מועצה
    -0.06
    POSITIVE LOGITS
    传奇
    0.08
    двига
    0.07
     ThreadPool
    0.07
    Choice
    0.07
     imageSize
    0.07
     grassroots
    0.07
    جار
    0.07
    (Form
    0.07
    jack
    0.06
     Gerard
    0.06
    Activations Density 0.033%

    No Known Activations