© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RESID-POST-AA
    11. 40997
    Prev
    Next
    INDEX
    Explanations

    ReactDOM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RaisePropertyChanged
    -0.07
    -reported
    -0.07
     Мо
    -0.07
     vc
    -0.07
     ,↵
    -0.07
     BuzzFeed
    -0.07
     shows
    -0.07
    mouseout
    -0.06
    _ERRORS
    -0.06
    瘳
    -0.06
    POSITIVE LOGITS
     serviços
    0.07
     restrictions
    0.07
    rectangle
    0.07
     أو
    0.07
    -government
    0.07
     intest
    0.07
    促进
    0.07
    opération
    0.06
     sevent
    0.06
    Diamond
    0.06
    Activations Density 0.001%

    No Known Activations