© 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. 127968
    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
    (per
    -0.07
    十五
    -0.07
    一段时间
    -0.07
    会不会
    -0.07
    大海
    -0.06
    旭
    -0.06
     دقائق
    -0.06
    生怕
    -0.06
    Tiny
    -0.06
    NECT
    -0.06
    POSITIVE LOGITS
     clickable
    0.07
    擊
    0.07
    	do
    0.07
     atroc
    0.07
    强制
    0.07
     apologise
    0.06
     источ
    0.06
     owned
    0.06
     property
    0.06
    idable
    0.06
    Activations Density 0.004%

    No Known Activations