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. 11-RESID-POST-AA
    6. 25050
    Prev
    Next
    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .iso
    -0.07
     hypo
    -0.07
     conceived
    -0.07
    herits
    -0.07
    trie
    -0.07
    出击
    -0.07
     происходит
    -0.07
     cher
    -0.07
     изготов
    -0.07
    عالج
    -0.07
    POSITIVE LOGITS
     Raf
    0.07
     efficient
    0.06
     Tes
    0.06
    Remark
    0.06
    .rooms
    0.06
     Quad
    0.06
    𝖖
    0.06
    (points
    0.06
     restr
    0.06
    𝐜
    0.06
    Activations Density 0.000%

    No Known Activations