© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 69225
    Prev
    Next
    INDEX
    Explanations

    say "}"

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Pharmac
    -0.07
     populist
    -0.07
     veggies
    -0.07
     professionnel
    -0.07
     troops
    -0.07
     notion
    -0.06
     Coch
    -0.06
     Setup
    -0.06
     власти
    -0.06
    .Flow
    -0.06
    POSITIVE LOGITS
    �
    0.06
     QR
    0.06
    꿴
    0.06
    也可
    0.06
    단
    0.06
    �
    0.06
    짼
    0.06
    았
    0.06
     שאי
    0.06
    DK
    0.06
    Activations Density 0.004%

    No Known Activations