© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40090
    Prev
    Next
    INDEX
    Explanations

    in

    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
    (instruction
    -0.07
     ullam
    -0.07
    PRI
    -0.07
     idea
    -0.07
    	Optional
    -0.06
    rias
    -0.06
    而已
    -0.06
    ʿ
    -0.06
    产销
    -0.06
    aar
    -0.06
    POSITIVE LOGITS
     GER
    0.08
    ewitness
    0.07
     رد
    0.07
     robber
    0.07
     BlackBerry
    0.07
    dddd
    0.07
    diğini
    0.07
    百度
    0.06
    IMIZE
    0.06
    grily
    0.06
    Activations Density 0.106%

    No Known Activations