© 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. 15-RESID-POST-AA
    6. 23761
    Prev
    Next
    INDEX
    Explanations

    royalty

    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
     кач
    -0.08
    _timeline
    -0.07
     oluş
    -0.07
    ʵ
    -0.07
    れない
    -0.07
     turf
    -0.07
    🎈
    -0.07
    real
    -0.07
    альным
    -0.07
    憑
    -0.07
    POSITIVE LOGITS
    _kwargs
    0.07
    PH
    0.07
     Sue
    0.07
     pathogens
    0.07
    쓴
    0.07
     ISO
    0.07
    Placeholder
    0.07
    的作用
    0.07
     loadData
    0.06
    ὀ
    0.06
    Activations Density 0.056%

    No Known Activations