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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 130663
    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
     ServiceException
    -0.07
    纵向
    -0.07
    ꦆ
    -0.07
    (datas
    -0.07
     coordinator
    -0.07
     Israelis
    -0.07
     Friendship
    -0.07
     Classification
    -0.07
     widening
    -0.07
    (nextProps
    -0.07
    POSITIVE LOGITS
    Little
    0.06
    锂
    0.06
    食
    0.06
    uglify
    0.06
    رام
    0.06
    adol
    0.06
    아
    0.06
    ()
    ↵
    ↵
    0.06
     знать
    0.06
    應
    0.06
    Activations Density 0.011%

    No Known Activations