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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 110245
    Prev
    Next
    INDEX
    Explanations

    PDO

    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
    一一
    -0.07
     UNIQUE
    -0.07
    iembre
    -0.07
    فعال
    -0.07
    GENERAL
    -0.07
     busca
    -0.07
    .people
    -0.06
    乖乖
    -0.06
     khoản
    -0.06
    纳斯
    -0.06
    POSITIVE LOGITS
     sprinkle
    0.07
     prof
    0.07
     universities
    0.07
    ṛ
    0.06
     ча
    0.06
     entrepreneurship
    0.06
     invaded
    0.06
    pv
    0.06
     intercepted
    0.06
    秉
    0.06
    Activations Density 0.001%

    No Known Activations