© 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. 7-RESID-POST-AA
    11. 39820
    Prev
    Next
    INDEX
    Explanations

    Jarvis

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -policy
    -0.07
    全面落实
    -0.07
    ễn
    -0.07
     Advantage
    -0.07
     исп
    -0.07
    �
    -0.07
     compensate
    -0.07
     Burr
    -0.07
    .blocks
    -0.07
    헵
    -0.07
    POSITIVE LOGITS
    ffi
    0.08
    'o
    0.07
    qui
    0.07
    antity
    0.07
     day
    0.07
    'e
    0.07
    аст
    0.07
    ди
    0.07
    每年
    0.07
    'in
    0.06
    Activations Density 0.001%

    No Known Activations