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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RESID-POST-AA
    6. 30070
    Prev
    Next
    INDEX
    Explanations

    Code

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     위한
    -0.07
    胡
    -0.07
     tornado
    -0.06
     وهي
    -0.06
     Instit
    -0.06
     Adler
    -0.06
     фирм
    -0.06
     Organisation
    -0.06
    いか
    -0.06
     reverted
    -0.06
    POSITIVE LOGITS
    ﺥ
    0.07
    תשע
    0.07
    _HORIZONTAL
    0.07
    搬到
    0.07
    Ю
    0.07
    .graphics
    0.07
    _ELEMENTS
    0.07
     Contacts
    0.07
    سا
    0.06
     jam
    0.06
    Activations Density 0.154%

    No Known Activations