© 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. 62291
    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
    .dropdown
    -0.07
     homic
    -0.07
    curring
    -0.07
     diverse
    -0.07
    episode
    -0.06
     Aydın
    -0.06
    _adv
    -0.06
     Prometheus
    -0.06
     þ
    -0.06
    POINT
    -0.06
    POSITIVE LOGITS
    חלוקת
    0.07
    }");↵
    0.07
    色彩
    0.07
    )")↵
    0.07
    ));↵↵
    0.07
    ));
    ↵
    ↵
    0.07
     ";
    ↵
    0.07
    atrib
    0.06
    냇
    0.06
     денег
    0.06
    Activations Density 0.018%

    No Known Activations