© 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. 59928
    Prev
    Next
    INDEX
    Explanations

    reflection

    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
    פח
    -0.08
    .asp
    -0.07
    どう
    -0.07
    findBy
    -0.07
    יז
    -0.07
    מט
    -0.07
    三农
    -0.07
    大幅提升
    -0.07
     credited
    -0.07
    -md
    -0.07
    POSITIVE LOGITS
     preacher
    0.07
     lux
    0.07
     فقال
    0.06
     Hibernate
    0.06
    ]int
    0.06
     (((
    0.06
    硕士研究
    0.06
    bd
    0.06
     safari
    0.06
     whip
    0.06
    Activations Density 0.005%

    No Known Activations