Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 7388
    Prev
    Next
    INDEX
    Explanations

    War

    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
     Podesta
    -0.08
    budget
    -0.08
     конкрет
    -0.08
    缮
    -0.07
     deepen
    -0.07
     brief
    -0.07
    (CL
    -0.07
    بدو
    -0.07
    伶
    -0.07
    ཁ
    -0.07
    POSITIVE LOGITS
    жи
    0.08
    除
    0.07
    뺴
    0.07
    交互
    0.07
    ispiel
    0.06
     expl
    0.06
     Initiative
    0.06
    sink
    0.06
    essen
    0.06
     inval
    0.06
    Activations Density 0.003%

    No Known Activations