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. 2419
    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
     אלף
    -0.07
    lösung
    -0.07
    Reached
    -0.07
    骨骼
    -0.07
    的眼睛
    -0.07
     estimation
    -0.06
     scored
    -0.06
    彩神
    -0.06
    太大
    -0.06
    烺
    -0.06
    POSITIVE LOGITS
     añ
    0.07
    Unit
    0.07
    OMPI
    0.07
     clients
    0.06
    _Entity
    0.06
    join
    0.06
     concat
    0.06
     hide
    0.06
    ppv
    0.06
     DISCLAIMER
    0.06
    Activations Density 0.011%

    No Known Activations