© 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. 53199
    Prev
    Next
    INDEX
    Explanations

    if

    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
    甘肃
    -0.07
     مايو
    -0.07
     Proceed
    -0.07
    uest
    -0.07
    המל
    -0.06
     Rupert
    -0.06
     Mango
    -0.06
     raspberry
    -0.06
    不甘
    -0.06
     cement
    -0.06
    POSITIVE LOGITS
    [])
↵
    0.07
    hos
    0.07
    tek
    0.07
    ()][
    0.07
    	cfg
    0.07
    خم
    0.07
    شك
    0.07
    Orientation
    0.07
     memes
    0.07
    itori
    0.07
    Activations Density 0.002%

    No Known Activations