© 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. 47949
    Prev
    Next
    INDEX
    Explanations

    data analysis

    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
    鞋
    -0.08
     experi
    -0.07
    财报
    -0.07
    霉
    -0.07
    多半
    -0.07
    companyId
    -0.07
    (enabled
    -0.07
    (stats
    -0.07
    ﮏ
    -0.07
     shoes
    -0.07
    POSITIVE LOGITS
     Jer
    0.07
     треть
    0.07
    ”:
    0.06
    olic
    0.06
    突如其来
    0.06
    丕
    0.06
    nes
    0.06
    actual
    0.06
    气势
    0.06
     cận
    0.06
    Activations Density 0.231%

    No Known Activations