© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    6. 80464
    Prev
    Next
    INDEX
    Explanations

    const

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始
    -0.07
     hepat
    -0.07
    rellas
    -0.07
     swept
    -0.07
    ﺴ
    -0.07
    ╄
    -0.07
    قص
    -0.06
     thoroughly
    -0.06
    fäll
    -0.06
     massively
    -0.06
    POSITIVE LOGITS
     <![
    0.07
     restrictions
    0.07
    千方百计
    0.07
     nex
    0.07
     strerror
    0.07
    酿
    0.07
    酝
    0.07
    .createTextNode
    0.07
     reminders
    0.07
     License
    0.07
    Activations Density 0.021%

    No Known Activations