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. 57114
    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
    	boolean
    -0.07
    #
    ↵
    -0.07
    REFERENCE
    -0.07
     giữa
    -0.07
     Suppose
    -0.06
    借款
    -0.06
    ↵↵
    -0.06
     với
    -0.06
    	Context
    -0.06
    分別
    -0.06
    POSITIVE LOGITS
    ILogger
    0.08
     Gray
    0.07
     Hari
    0.07
     ANN
    0.07
     Ingram
    0.07
     betrayal
    0.07
    ARK
    0.07
     Alam
    0.07
     bloss
    0.07
    irectional
    0.07
    Activations Density 0.000%

    No Known Activations