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. 131056
    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
     Gil
    -0.07
     staring
    -0.07
     dof
    -0.07
    _IO
    -0.07
     البر
    -0.07
    itti
    -0.06
     pien
    -0.06
    dził
    -0.06
     pathological
    -0.06
     zen
    -0.06
    POSITIVE LOGITS
    |
    ↵
    0.07
     flows
    0.07
    》
    0.07
    owners
    0.07
    Collections
    0.07
    bj
    0.07
     комф
    0.07
    低成本
    0.07
     |
    ↵
    0.07
     Often
    0.06
    Activations Density 0.000%

    No Known Activations