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. 88273
    Prev
    Next
    INDEX
    Explanations

    providing a service

    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
     trance
    -0.08
     رسالة
    -0.08
    салон
    -0.07
    impact
    -0.07
     lumière
    -0.07
    licity
    -0.07
    наци
    -0.07
    .LOG
    -0.07
    nç
    -0.07
    保荐
    -0.07
    POSITIVE LOGITS
    Qt
    0.07
     healthy
    0.07
     عبدالله
    0.07
    ola
    0.07
    旅游度假
    0.07
    (\"
    0.06
    rible
    0.06
    泄
    0.06
     though
    0.06
    uku
    0.06
    Activations Density 0.101%

    No Known Activations