© 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. 19-RESID-POST-AA
    11. 89726
    Prev
    Next
    INDEX
    Explanations

    rate

    np_max-act-logits · gemini-2.0-flash
    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
    _MIN
    -0.07
     Inspector
    -0.07
    iek
    -0.06
     Soldiers
    -0.06
     disclaimer
    -0.06
     migration
    -0.06
    争霸
    -0.06
     thông
    -0.06
    _speed
    -0.06
    ecd
    -0.06
    POSITIVE LOGITS
     Сер
    0.08
    介绍了
    0.07
    ('/')[-
    0.07
    彬
    0.07
    其中包括
    0.07
     İşte
    0.07
     Со
    0.07
    крыл
    0.07
    atin
    0.07
    瞭解
    0.07
    Activations Density 0.011%

    No Known Activations