© 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. 127602
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    熻
    -0.07
     mig
    -0.07
     hin
    -0.07
     PIC
    -0.07
    Expires
    -0.06
    第七
    -0.06
     DG
    -0.06
    采
    -0.06
    MG
    -0.06
     banning
    -0.06
    POSITIVE LOGITS
    erties
    0.07
    KeySpec
    0.07
    前所未
    0.07
    صار
    0.06
    itions
    0.06
    ength
    0.06
    呼和浩特
    0.06
    osc
    0.06
    得到了
    0.06
    ankan
    0.06
    Activations Density 0.020%

    No Known Activations