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. 15-RESID-POST-AA
    6. 128078
    Prev
    Next
    INDEX
    Explanations

    ram

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ǐ
    -0.07
    最为
    -0.07
     spear
    -0.07
    obre
    -0.07
    比较简单
    -0.07
    未能
    -0.07
    mit
    -0.07
    paint
    -0.07
    tá
    -0.07
    ENO
    -0.07
    POSITIVE LOGITS
    -*
    0.07
     Laws
    0.07
     (*
    0.07
    dığımız
    0.07
    法案
    0.07
    城县
    0.07
     Folder
    0.07
     proposed
    0.07
    ปลา
    0.06
    Ports
    0.06
    Activations Density 0.000%

    No Known Activations