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. 19-RESID-POST-AA
    6. 129768
    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_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
     enraged
    -0.08
    itm
    -0.08
     tik
    -0.07
    тир
    -0.07
    豺
    -0.07
     Produto
    -0.07
    器具
    -0.07
     Chung
    -0.07
     psycho
    -0.07
     müd
    -0.07
    POSITIVE LOGITS
    ック
    0.07
    GridLayout
    0.07
    ####
    0.07
    Recent
    0.07
    	Value
    0.07
    client
    0.07
    ượt
    0.06
    Л
    0.06
    开奖
    0.06
    Less
    0.06
    Activations Density 0.001%

    No Known Activations