© 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. 12332
    Prev
    Next
    INDEX
    Explanations

    I

    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
     scour
    -0.07
     hoop
    -0.07
     detective
    -0.07
     Tracks
    -0.06
    ены
    -0.06
    絮
    -0.06
     worksheets
    -0.06
    👔
    -0.06
    сы
    -0.06
    艉
    -0.06
    POSITIVE LOGITS
    Vars
    0.07
    �
    0.07
    UGINS
    0.07
    )a
    0.07
    得了
    0.06
    PropertyChanged
    0.06
     oldukları
    0.06
     embryo
    0.06
    ⇙
    0.06
    enstein
    0.06
    Activations Density 0.117%

    No Known Activations