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. 70570
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical writing

    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
    achel
    -0.07
    空气质量
    -0.07
     quizzes
    -0.07
     enhances
    -0.07
     constructing
    -0.07
     اسم
    -0.07
     annual
    -0.07
    addClass
    -0.07
     Polish
    -0.07
     باسم
    -0.07
    POSITIVE LOGITS
     Sta
    0.08
    ��
    0.07
    £o
    0.07
    مواجه
    0.07
    dma
    0.07
    _ratings
    0.07
    unkt
    0.06
    Fant
    0.06
     Modifier
    0.06
     inte
    0.06
    Activations Density 0.094%

    No Known Activations