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. 129524
    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
    仅代表
    -0.08
    ematics
    -0.08
    leetcode
    -0.07
    notify
    -0.07
    agree
    -0.07
    gly
    -0.07
    不出来
    -0.07
    sizei
    -0.07
    🦄
    -0.07
     Economics
    -0.07
    POSITIVE LOGITS
    ⴼ
    0.07
     Valk
    0.06
     Mig
    0.06
    ẫ
    0.06
    paged
    0.06
     rubble
    0.06
     material
    0.06
     deceit
    0.06
    战
    0.06
    塄
    0.06
    Activations Density 0.002%

    No Known Activations