© 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. 7-RESID-POST-AA
    11. 80239
    Prev
    Next
    INDEX
    Explanations

    Love

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    硙
    -0.07
     nei
    -0.07
    往前
    -0.07
    理事
    -0.07
     researching
    -0.07
    弊
    -0.07
    ıntı
    -0.07
    Bloc
    -0.07
    瞻
    -0.07
    缶
    -0.06
    POSITIVE LOGITS
    ыв
    0.08
     Autom
    0.07
    promo
    0.07
    .EntityManager
    0.07
     anticip
    0.07
     HSV
    0.07
     MF
    0.07
     потреб
    0.07
     установ
    0.07
     invert
    0.07
    Activations Density 0.011%

    No Known Activations