© 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. 11-RESID-POST-AA
    11. 40881
    Prev
    Next
    INDEX
    Explanations

    Asking if it's correct

    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
     Moore
    -0.07
     advertisers
    -0.07
     container
    -0.07
    Mapping
    -0.07
     Siri
    -0.07
    绨
    -0.07
     cela
    -0.07
     entitlement
    -0.07
     constraints
    -0.07
    鲹
    -0.07
    POSITIVE LOGITS
     young
    0.07
    反映了
    0.06
     inkl
    0.06
    ay
    0.06
    鼙
    0.06
     ¡
    0.06
     /**↵
    0.06
    look
    0.06
     /**
↵
    0.06
    angepicker
    0.06
    Activations Density 0.070%

    No Known Activations