© 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. 48053
    Prev
    Next
    INDEX
    Explanations

    charts and data

    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
    深厚
    -0.07
    TargetException
    -0.07
    𨱑
    -0.07
    leared
    -0.07
    列车
    -0.06
    _section
    -0.06
    浕
    -0.06
     TERMS
    -0.06
    摽
    -0.06
    ᡤ
    -0.06
    POSITIVE LOGITS
    participant
    0.08
    体重
    0.08
    BMI
    0.08
    Around
    0.07
     problematic
    0.07
    Potential
    0.07
    Quantity
    0.07
    绩
    0.07
     punk
    0.07
     Pins
    0.07
    Activations Density 0.005%

    No Known Activations