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

    Neuronpedia

    Jacobian LensNEW
    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. 15-RESID-POST-AA
    11. 16523
    Prev
    Next
    INDEX
    Explanations

    setup

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    جمع
    -0.08
     investor
    -0.07
    Celebr
    -0.07
     Angie
    -0.07
    ถ
    -0.07
     notwithstanding
    -0.07
    스트
    -0.07
    /**
    -0.07
     Heard
    -0.07
    تكامل
    -0.07
    POSITIVE LOGITS
    -An
    0.07
     Uk
    0.07
     setup
    0.07
    Ӎ
    0.07
     QQ
    0.07
    ],$
    0.07
     silenced
    0.07
     realities
    0.07
    -top
    0.07
    核
    0.07
    Activations Density 0.010%

    No Known Activations