© 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. 13897
    Prev
    Next
    INDEX
    Explanations

    say '. word'

    np_max-act-logits · gemini-2.0-flash
    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
    ้า
    -0.08
     superior
    -0.07
    .Resize
    -0.07
    classic
    -0.07
    慌
    -0.07
    lections
    -0.07
     unravel
    -0.07
    $b
    -0.07
     yanlış
    -0.07
    quests
    -0.07
    POSITIVE LOGITS
    鋈
    0.07
     Skeleton
    0.07
    根據
    0.07
    CJK
    0.06
    .drawImage
    0.06
    就会
    0.06
    	pthread
    0.06
     החיים
    0.06
     נתונים
    0.06
     discharged
    0.06
    Activations Density 0.000%

    No Known Activations