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. 129573
    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
    疢
    -0.07
    _finder
    -0.07
     bạc
    -0.07
    /******/
    -0.07
     Workflow
    -0.07
     INFORMATION
    -0.07
     AutoMapper
    -0.07
     precondition
    -0.07
     Yemen
    -0.07
    はずです
    -0.06
    POSITIVE LOGITS
     conducts
    0.07
    .")
    ↵
    0.07
    _min
    0.07
    Steve
    0.07
    oden
    0.06
    Padding
    0.06
    旗
    0.06
    缡
    0.06
    含
    0.06
    省
    0.06
    Activations Density 0.000%

    No Known Activations