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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 76917
    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
    Entre
    -0.07
     licensing
    -0.07
    瀏覽
    -0.07
     Tail
    -0.07
    ebb
    -0.07
    一身
    -0.07
    /setup
    -0.07
    흉
    -0.07
    誓言
    -0.07
    寿
    -0.06
    POSITIVE LOGITS
     intermediate
    0.08
     threw
    0.07
    ughs
    0.07
    azine
    0.07
     Na
    0.07
     transformer
    0.07
    	boolean
    0.07
     laughs
    0.07
     loosen
    0.07
     stimulated
    0.07
    Activations Density 0.242%

    No Known Activations