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. 19-RESID-POST-AA
    6. 130471
    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
    ゛
    -0.07
    ✜
    -0.07
    缣
    -0.07
     noi
    -0.07
     azi
    -0.06
     Cert
    -0.06
    .FileNotFoundException
    -0.06
    趴
    -0.06
     DevComponents
    -0.06
     MetroFramework
    -0.06
    POSITIVE LOGITS
    OPS
    0.08
    small
    0.07
     HEIGHT
    0.07
    .import
    0.07
     invocation
    0.07
    .reduce
    0.07
     он
    0.06
    曲
    0.06
    .Language
    0.06
    .spark
    0.06
    Activations Density 0.001%

    No Known Activations