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. 88307
    Prev
    Next
    INDEX
    Explanations

    Calculating time

    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
    学习成绩
    -0.08
    حصل
    -0.08
    菘
    -0.07
    どうしても
    -0.07
    官司
    -0.07
    国情
    -0.07
    🐵
    -0.07
     piger
    -0.07
    .firstChild
    -0.07
     choice
    -0.06
    POSITIVE LOGITS
    motor
    0.08
     Seg
    0.07
     cipher
    0.07
     visc
    0.07
    Bluetooth
    0.07
    dimension
    0.07
     patch
    0.07
    :len
    0.07
    ||||
    0.06
     frames
    0.06
    Activations Density 0.093%

    No Known Activations