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. 7192
    Prev
    Next
    INDEX
    Explanations

    social welfare/services

    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
    اصر
    -0.07
    _EDITOR
    -0.07
    +"<
    -0.07
    鸮
    -0.06
    !!)↵
    -0.06
     đoán
    -0.06
     manuscript
    -0.06
    getSimpleName
    -0.06
     país
    -0.06
    故宫
    -0.06
    POSITIVE LOGITS
    民
    0.08
    ">&
    0.07
    /www
    0.07
     Making
    0.07
     scenic
    0.07
     Corp
    0.07
    _From
    0.07
     STEP
    0.07
     fireEvent
    0.07
    poke
    0.07
    Activations Density 0.059%

    No Known Activations