© 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. 52456
    Prev
    Next
    INDEX
    Explanations

    robots

    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
     đốc
    -0.08
    CommandLine
    -0.07
     Renaissance
    -0.07
     살
    -0.07
     Narendra
    -0.07
     demographics
    -0.07
    創新
    -0.07
    BoundingBox
    -0.07
    着眼
    -0.06
     lombok
    -0.06
    POSITIVE LOGITS
    ރ
    0.07
    쌰
    0.07
     FOUND
    0.07
    锶
    0.06
    porno
    0.06
    unistd
    0.06
    调查显示
    0.06
    偿还
    0.06
    味道
    0.06
     שכבר
    0.06
    Activations Density 0.026%

    No Known Activations