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. 130916
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    不见
    -0.07
    指的是
    -0.07
    届时
    -0.07
    .loadtxt
    -0.07
    打造
    -0.07
    hits
    -0.07
    /uploads
    -0.07
    紧接着
    -0.06
    镛
    -0.06
    /media
    -0.06
    POSITIVE LOGITS
    —if
    0.07
    _System
    0.07
    潛
    0.06
     safety
    0.06
    —which
    0.06
    imageName
    0.06
    החזר
    0.06
    Short
    0.06
    Reservation
    0.06
    _lng
    0.06
    Activations Density 0.028%

    No Known Activations