© 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. 15-RESID-POST-AA
    11. 81314
    Prev
    Next
    INDEX
    Explanations

    Technical/business data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     salads
    -0.08
    .ui
    -0.07
     Xia
    -0.07
     rank
    -0.07
     SetUp
    -0.07
    溽
    -0.06
    ango
    -0.06
    .radius
    -0.06
    ทรง
    -0.06
     cada
    -0.06
    POSITIVE LOGITS
    ⇃
    0.07
    Correction
    0.06
     collection
    0.06
    疍
    0.06
    发财
    0.06
    great
    0.06
    兼容
    0.06
    不良信息
    0.06
    新型冠状
    0.06
    職
    0.06
    Activations Density 0.301%

    No Known Activations