© 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. 15-RESID-POST-AA
    11. 129568
    Prev
    Next
    INDEX
    Explanations

    -inflammatory

    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
    /head
    -0.07
    稼
    -0.07
     brave
    -0.07
    恶劣
    -0.07
    de
    -0.06
     THIS
    -0.06
    (/
    -0.06
    createElement
    -0.06
    坚强
    -0.06
    代表性
    -0.06
    POSITIVE LOGITS
    ookies
    0.07
     currently
    0.07
    <String
    0.07
    oggled
    0.07
     Reds
    0.07
     אינם
    0.07
     proxies
    0.07
     Creatures
    0.06
    peria
    0.06
    рем
    0.06
    Activations Density 0.002%

    No Known Activations