© 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. 19-RESID-POST-AA
    11. 3153
    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
    孵化
    -0.08
    准备好
    -0.08
    医学院
    -0.08
    婻
    -0.07
    天府
    -0.07
     söyle
    -0.07
     سن
    -0.07
    到来
    -0.07
     bacheca
    -0.06
     대통
    -0.06
    POSITIVE LOGITS
     Pur
    0.07
    Purpose
    0.07
    (sf
    0.06
    及び
    0.06
    cit
    0.06
    paragraph
    0.06
    sus
    0.06
    ullets
    0.06
    Sol
    0.06
     Appet
    0.06
    Activations Density 0.002%

    No Known Activations