© 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. 77855
    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
    .misc
    -0.07
    瞟
    -0.07
    antar
    -0.07
     preparedStatement
    -0.07
     entails
    -0.07
     fluffy
    -0.07
    (dic
    -0.07
    擁有
    -0.07
    Let
    -0.07
    /Desktop
    -0.06
    POSITIVE LOGITS
     Rome
    0.07
     Sales
    0.07
    method
    0.07
     Carlo
    0.07
    杀了
    0.06
     vuel
    0.06
    受伤
    0.06
    roat
    0.06
    윁
    0.06
     Buenos
    0.06
    Activations Density 0.069%

    No Known Activations