© 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. 19-RESID-POST-AA
    11. 72115
    Prev
    Next
    INDEX
    Explanations

    Regents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    雯
    -0.08
    .Sort
    -0.07
    ''↵
    -0.07
    挥手
    -0.07
    buie
    -0.07
    HV
    -0.07
     manuals
    -0.07
    血
    -0.07
     Mach
    -0.07
     ngủ
    -0.07
    POSITIVE LOGITS
     configuration
    0.07
    потреб
    0.06
     Example
    0.06
     Coun
    0.06
    发展战略
    0.06
    _'.$
    0.06
     Patent
    0.06
    אוגוסט
    0.06
     doctrine
    0.06
     geleceği
    0.06
    Activations Density 0.001%

    No Known Activations