© 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. 72148
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
     müdah
    -0.08
    滨江
    -0.07
     "<
    -0.07
     chiar
    -0.07
    红豆
    -0.07
    忤
    -0.07
    笞
    -0.07
     yayımla
    -0.07
    会展中心
    -0.07
     reminder
    -0.07
    POSITIVE LOGITS
     workouts
    0.08
     Jer
    0.07
    Emitter
    0.07
    amel
    0.07
    ﻡ
    0.07
    מים
    0.07
    __)
    0.07
     Fal
    0.06
    ários
    0.06
    Attempting
    0.06
    Activations Density 0.019%

    No Known Activations