© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 75890
    Prev
    Next
    INDEX
    Explanations

    as

    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
    ﴿
    -0.08
    (Tree
    -0.07
     دي
    -0.07
     onze
    -0.06
     tot
    -0.06
     dai
    -0.06
    Teacher
    -0.06
    检察官
    -0.06
     zoek
    -0.06
    造福
    -0.06
    POSITIVE LOGITS
    pleasant
    0.08
    سئل
    0.08
    <Application
    0.07
     level
    0.07
    하시
    0.07
     아래
    0.07
    Fall
    0.07
     troublesome
    0.07
    Subscriber
    0.07
    下面
    0.07
    Activations Density 0.018%

    No Known Activations