Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 49875
    Prev
    Next
    INDEX
    Explanations

    court

    np_max-act · gemini-2.0-flash
    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
     of
    -0.08
     уч
    -0.07
     subscribe
    -0.07
    -sup
    -0.07
     Ч
    -0.07
    ssl
    -0.07
    _balance
    -0.07
    神州
    -0.07
     belong
    -0.07
    _lambda
    -0.07
    POSITIVE LOGITS
     court
    0.09
     Court
    0.08
    科研院
    0.08
    器件
    0.08
     viewDidLoad
    0.08
     courts
    0.07
     courte
    0.07
    𝘤
    0.07
     courtyard
    0.07
     الخيار
    0.07
    Activations Density 0.037%

    No Known Activations