© 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. 44755
    Prev
    Next
    INDEX
    Explanations

    var

    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
    _death
    -0.07
    塌
    -0.07
    vp
    -0.07
    OTT
    -0.07
     Sullivan
    -0.07
    	struct
    -0.07
    lett
    -0.07
    ⊔
    -0.07
    flen
    -0.06
     cinnamon
    -0.06
    POSITIVE LOGITS
    تحويل
    0.07
     analys
    0.07
     SPI
    0.07
     contrasting
    0.07
    ๚
    0.07
     Tôi
    0.07
    Verifier
    0.07
    景象
    0.07
     align
    0.07
    Tôi
    0.06
    Activations Density 0.002%

    No Known Activations