© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 116707
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    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
     قوله
    -0.08
    .removeAttribute
    -0.08
    .surname
    -0.07
     starters
    -0.07
     tty
    -0.06
     prescriptions
    -0.06
    LEE
    -0.06
    춧
    -0.06
     거의
    -0.06
    .readLine
    -0.06
    POSITIVE LOGITS
    鍋
    0.07
    年
    0.07
    明亮
    0.07
    更快
    0.07
    进场
    0.07
    allery
    0.07
     öneri
    0.07
    这是我
    0.07
    订阅
    0.07
    副作用
    0.07
    Activations Density 0.005%

    No Known Activations