© 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
    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. 85587
    Prev
    Next
    INDEX
    Explanations

    Schiff

    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
     grille
    -0.07
    낱
    -0.07
     Trou
    -0.07
     assist
    -0.07
    Mb
    -0.07
                                                                    
    -0.07
    -bed
    -0.07
    抗击
    -0.07
     grö
    -0.07
     исполни
    -0.06
    POSITIVE LOGITS
     הקר
    0.07
    دس
    0.07
     ↔
    0.07
     ANT
    0.07
    等方式
    0.06
     đề
    0.06
     intention
    0.06
    cją
    0.06
     Plans
    0.06
     jealous
    0.06
    Activations Density 0.004%

    No Known Activations