© 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. 11-RESID-POST-AA
    11. 113844
    Prev
    Next
    INDEX
    Explanations

    Confirmation/messages being sent

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     dafür
    -0.08
     draped
    -0.07
     donating
    -0.07
     suppression
    -0.07
     Swimming
    -0.07
     dopo
    -0.07
     sophomore
    -0.07
     tutoring
    -0.07
    𪩘
    -0.07
     rating
    -0.07
    POSITIVE LOGITS
    ."/
    0.07
     GetComponent
    0.06
    に戻
    0.06
     King
    0.06
     stripslashes
    0.06
    userinfo
    0.06
     עסקים
    0.06
    会谈
    0.06
     !_
    0.06
    应收账
    0.06
    Activations Density 0.081%

    No Known Activations