© 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. 15-RESID-POST-AA
    11. 80515
    Prev
    Next
    INDEX
    Explanations

    computing operations

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    _SPR
    -0.07
    中医药
    -0.07
    阻力
    -0.07
     putt
    -0.07
    מנע
    -0.07
     Attend
    -0.07
    שמר
    -0.07
     Socialist
    -0.06
     матч
    -0.06
     pencils
    -0.06
    POSITIVE LOGITS
     JComboBox
    0.07
    ���
    0.07
     их
    0.07
    ected
    0.07
    冒出
    0.06
     unrestricted
    0.06
    .Require
    0.06
    הי
    0.06
     Herb
    0.06
    			↵
    0.06
    Activations Density 0.011%

    No Known Activations