© 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. 62679
    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
    悉尼
    -0.07
     اللغ
    -0.07
     المتحدة
    -0.07
     traded
    -0.07
    加州
    -0.07
    TagName
    -0.07
     pricing
    -0.07
    _VOID
    -0.07
     지역
    -0.06
    込む
    -0.06
    POSITIVE LOGITS
     instrument
    0.08
     estimator
    0.07
     pretrained
    0.07
    ровер
    0.07
     解
    0.07
     fanc
    0.07
    variant
    0.07
    estar
    0.06
    やら
    0.06
     lod
    0.06
    Activations Density 0.029%

    No Known Activations