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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RESID-POST-AA
    11. 77726
    Prev
    Next
    INDEX
    Explanations

    synthetic

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {
↵
↵
    -0.07
     Pref
    -0.06
     enormous
    -0.06
    著名的
    -0.06
    就不
    -0.06
     cones
    -0.06
     Persistence
    -0.06
    More
    -0.06
     deem
    -0.06
     amb
    -0.06
    POSITIVE LOGITS
    经常会
    0.09
     détail
    0.08
    (figsize
    0.07
    注册资本
    0.07
     atan
    0.07
    鹟
    0.07
     spectro
    0.07
    鹂
    0.07
    illez
    0.07
     sunscreen
    0.07
    Activations Density 0.002%

    No Known Activations