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. 15-RESID-POST-AA
    6. 56630
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ren
    -0.07
     hell
    -0.07
     reuseIdentifier
    -0.07
    jspx
    -0.07
     ואני
    -0.07
    альная
    -0.06
    ないと
    -0.06
    	glm
    -0.06
     Indianapolis
    -0.06
    سرعة
    -0.06
    POSITIVE LOGITS
    _Array
    0.07
    飞行
    0.07
    roupe
    0.07
    (results
    0.06
    faq
    0.06
    és
    0.06
    _assign
    0.06
    ios
    0.06
    检查
    0.06
    阅历
    0.06
    Activations Density 0.008%

    No Known Activations