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. 70774
    Prev
    Next
    INDEX
    Explanations

    connect

    np_max-act-logits · gemini-2.0-flash
    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
     appealed
    -0.07
    醨
    -0.07
    黻
    -0.07
    ﭭ
    -0.07
     której
    -0.06
    araoh
    -0.06
    Leader
    -0.06
    合法权益
    -0.06
    主公
    -0.06
    (interp
    -0.06
    POSITIVE LOGITS
    iosity
    0.07
    pair
    0.07
     trimest
    0.07
    旱
    0.06
     responsiveness
    0.06
     rộng
    0.06
    ZN
    0.06
    .Linq
    0.06
     Shell
    0.06
     Risk
    0.06
    Activations Density 0.001%

    No Known Activations