© 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. 84907
    Prev
    Next
    INDEX
    Explanations

    reuters

    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
    附加
    -0.07
    항
    -0.07
    我不知道
    -0.06
    [random
    -0.06
    决胜
    -0.06
    connector
    -0.06
     Interactive
    -0.06
    的优势
    -0.06
    מלי
    -0.06
    سيطر
    -0.06
    POSITIVE LOGITS
    adium
    0.07
     befind
    0.07
    查阅
    0.07
     Birch
    0.06
     nao
    0.06
     stad
    0.06
    三百
    0.06
    やす
    0.06
     dz
    0.06
    烶
    0.06
    Activations Density 0.001%

    No Known Activations