© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 554
    Prev
    Next
    INDEX
    Explanations

    mathematical contexts

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _UL
    -0.07
    .DataAccess
    -0.07
     isValid
    -0.07
    ハウ
    -0.07
    充裕
    -0.07
     się
    -0.07
    这类
    -0.07
    טייל
    -0.07
    _PHP
    -0.07
    ylland
    -0.07
    POSITIVE LOGITS
    answers
    0.08
     лечение
    0.08
     meanings
    0.07
    密码
    0.07
    /T
    0.07
    经营范围
    0.06
    ivors
    0.06
     Compatible
    0.06
    自觉
    0.06
    自我
    0.06
    Activations Density 0.055%

    No Known Activations