Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 131051
    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_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
     Producto
    -0.07
    ым
    -0.06
    鋆
    -0.06
     accustomed
    -0.06
    קו
    -0.06
    海拔
    -0.06
    %)
    -0.06
    出产
    -0.06
    -route
    -0.06
    ams
    -0.06
    POSITIVE LOGITS
     woll
    0.07
    \'
    0.07
     FIN
    0.07
     secretly
    0.06
     spit
    0.06
     MAY
    0.06
    EObject
    0.06
    美的
    0.06
     syntax
    0.06
    Њ
    0.06
    Activations Density 0.003%

    No Known Activations