© 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. 77580
    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
     typings
    -0.08
     government
    -0.07
    /setup
    -0.07
    微博
    -0.07
     typingsJapgolly
    -0.07
     bass
    -0.07
     Marr
    -0.07
    ential
    -0.07
    國內
    -0.07
     Warcraft
    -0.06
    POSITIVE LOGITS
    …but
    0.07
    发财
    0.07
    ✡
    0.07
    包袱
    0.07
    _fault
    0.07
     Struct
    0.07
    interpre
    0.06
    忠诚
    0.06
    出现问题
    0.06
    complex
    0.06
    Activations Density 0.025%

    No Known Activations