© 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. 15-RESID-POST-AA
    11. 77843
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     expect
    -0.07
     Ambassador
    -0.07
     Expected
    -0.07
     Anchor
    -0.07
    ,out
    -0.07
    asp
    -0.07
     advise
    -0.07
     IData
    -0.07
    赞叹
    -0.06
    (async
    -0.06
    POSITIVE LOGITS
    埚
    0.08
    Enemies
    0.07
    FixedSize
    0.07
     searchBar
    0.07
    好友
    0.07
     النواب
    0.07
    依然
    0.07
    esterday
    0.07
    Mode
    0.07
    eba
    0.07
    Activations Density 0.055%

    No Known Activations