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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24580
    Prev
    Next
    INDEX
    Explanations

    Italian language

    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
    _combo
    -0.08
    삔
    -0.07
    владе
    -0.07
     Consultant
    -0.07
     Bài
    -0.07
     Gauss
    -0.07
    ދ
    -0.07
    嗽
    -0.07
     distingu
    -0.07
    蹁
    -0.06
    POSITIVE LOGITS
    .info
    0.07
    錄
    0.07
     הבי
    0.07
    TA
    0.07
    ってしまいます
    0.07
    _logs
    0.07
    	bytes
    0.06
     tb
    0.06
     napisał
    0.06
     VERBOSE
    0.06
    Activations Density 0.004%

    No Known Activations